url stringlengths 11 2.25k | text stringlengths 88 50k | ts timestamp[s]date 2026-01-13 08:47:33 2026-01-13 09:30:40 |
|---|---|---|
https://jp.linkedin.com/company/cloudflare | Cloudflare | LinkedIn メインコンテンツにスキップ LinkedIn 記事 ユーザー ラーニング 求人 ゲーム サインイン 無料で登録 Cloudflare コンピューター・ネットワークセキュリティ San Francisco、California 1,123,490人のフォロワー Cloudflareが目指すのは、より良いインターネットの構築に貢献すること。 求人を表示 フォローする 6,532人すべての社員を表示 この会社を報告する 概要 求人 カルチャー 概要 Cloudflare, Inc. (NYSE: NET) is the leading connectivity cloud company. It empowers organizations to make their employees, applications and networks faster and more secure everywhere, while reducing complexity and cost. Cloudflare’s connectivity cloud delivers the most full-featured, unified platform of cloud-native products and developer tools, so any organization can gain the control they need to work, develop, and accelerate their business. Powered by one of the world’s largest and most interconnected networks, Cloudflare blocks billions of threats online for its customers every day. It is trusted by millions of organizations – from the largest brands to entrepreneurs and small businesses to nonprofits, humanitarian groups, and governments across the globe. ウェブサイト https://www.cloudflare.com Cloudflareの外部リンク 業種 コンピューター・ネットワークセキュリティ 会社規模 社員 1,001 - 5,000名 本社 San Francisco、California 種類 上場企業 創立 2009 専門分野 nginx、lua、go、web performance、web security、dns、network, noc, nocc、ddos、CDN、waf、zero trust security、developer tools 製品 すべて表示 前のコンテンツはありません Argo Smart Routing、ネットワーク管理ソフトウェア Argo Smart Routing ネットワーク管理ソフトウェア Cloudflare Access、IDおよびアクセス管理 (IAM) ソフトウェア Cloudflare Access IDおよびアクセス管理 (IAM) ソフトウェア Cloudflare CDN、コンテンツデリバリーネットワーク (CDN) ソフトウェア Cloudflare CDN コンテンツデリバリーネットワーク (CDN) ソフトウェア Cloudflare DDoS Protection、DDoS保護ソフトウェア Cloudflare DDoS Protection DDoS保護ソフトウェア Cloudflare DNS、マネージドDNSサービスソフトウェア Cloudflare DNS マネージドDNSサービスソフトウェア Cloudflare Load Balancing、ロードバランシングソフトウェア Cloudflare Load Balancing ロードバランシングソフトウェア Cloudflare Registrar、マネージドDNSサービスソフトウェア Cloudflare Registrar マネージドDNSサービスソフトウェア Cloudflare Spectrum、DDoS保護ソフトウェア Cloudflare Spectrum DDoS保護ソフトウェア Cloudflare SSL / TLS、SSL資格ソフトウェア Cloudflare SSL / TLS SSL資格ソフトウェア Cloudflare Stream、ライブストリーミングソフトウェア Cloudflare Stream ライブストリーミングソフトウェア 次のコンテンツはありません 製品 Argo Smart Routing、ネットワーク管理ソフトウェア Argo Smart Routing ネットワーク管理ソフトウェア Cloudflare Access、IDおよびアクセス管理 (IAM) ソフトウェア Cloudflare Access IDおよびアクセス管理 (IAM) ソフトウェア Cloudflare CDN、コンテンツデリバリーネットワーク (CDN) ソフトウェア Cloudflare CDN コンテンツデリバリーネットワーク (CDN) ソフトウェア Cloudflare DDoS Protection、DDoS保護ソフトウェア Cloudflare DDoS Protection DDoS保護ソフトウェア Cloudflare DNS、マネージドDNSサービスソフトウェア Cloudflare DNS マネージドDNSサービスソフトウェア Cloudflare Load Balancing、ロードバランシングソフトウェア Cloudflare Load Balancing ロードバランシングソフトウェア Cloudflare Registrar、マネージドDNSサービスソフトウェア Cloudflare Registrar マネージドDNSサービスソフトウェア Cloudflare Spectrum、DDoS保護ソフトウェア Cloudflare Spectrum DDoS保護ソフトウェア Cloudflare SSL / TLS、SSL資格ソフトウェア Cloudflare SSL / TLS SSL資格ソフトウェア Cloudflare Stream、ライブストリーミングソフトウェア Cloudflare Stream ライブストリーミングソフトウェア Cloudflare WAF、ウェブアプリケーションファイアウォール (WAF) Cloudflare WAF ウェブアプリケーションファイアウォール (WAF) Cloudflare Web Analytics、デジタル分析ソフトウェア Cloudflare Web Analytics デジタル分析ソフトウェア Cloudflare Workers、サーバー仮想化ソフトウェア Cloudflare Workers サーバー仮想化ソフトウェア 場所 プライマリ 101 Townsend St San Francisco、California、94107、US 道順を表示 Westminster Bridge Road 6th Floor, Riverside Building, County Hall London、England、SE1 7PB、GB 道順を表示 120 Robinson Road Frasers Tower #35-01 Singapore、Singapore、069547、SG 道順を表示 405 Comal St Austin、Texas、78702、US 道順を表示 10 Almaden Blvd Suite 200 San Jose、California、95113、US 道順を表示 Rosental 7 Munich、Bavaria、80331、DE 道順を表示 301 N Neil St Suite 440 Champaign、Illinois、61820、US 道順を表示 26-1 Sakuragaoka-cho Shibuya-ku, Level 15 Cerulean Tower Tokyo、150-8512、JP 道順を表示 16 South Guangshun Street Donghuang Building 17th Floor Beijing、Chaoyang District Beijing、100015、CN 道順を表示 Rue de la Loi 38 Brussels、Brussels Region、1000、BE 道順を表示 Praça Marquês de Pombal 14 7th floor Lisbon、1250-162、PT 道順を表示 6, Place de la Madeleine Mailing Address Only Paris、Île-de-France、75008、FR 道順を表示 20 Martin Place Level 10 Sydney、NSW、2000、AU 道順を表示 1401 K St NW Washington、District of Columbia、20005、US 道順を表示 その他の場所を表示 場所を部分表示 Cloudflareの社員 Adam Edgmond Mark Nottingham Trevor Laughton Carl Ledbetter 全社員を表示 アップデート Cloudflare 1,123,490人のフォロワー 8時間前 この投稿について報告する As we kick off the new year, we’re spotlighting Cloudflare leaders across multiple functions who will share their insights around technical trends and emerging threats in 2026. 🎥 Nan Hao Maguire, APAC & Japan Field CTO at Cloudflare, breaks down the urgent shifts in the threat landscape, from smarter AI-driven attacks to the emerging reality of quantum computing. Discover our technical predictions for 2026 in our Post Quantum Computing solution brief: https://cfl.re/3LyW1eC #Cybersecurity #QuantumComputing #AI #FutureofTech #Infrastructure #2026Trends …さらに表示 25 2件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 14時間前 この投稿について報告する The margin is thinner than you think with modernizing applications. 📉 14% are behind schedule. 13% are ahead of schedule. This 1% difference can make or break your ability to innovate with AI. 🤖 Find out how in the 2026 Cloudflare App Innovation Report, dropping this Wednesday. 🚀 #AppInnovationReport #TechnologyInnovation #CyberSecurity 35 4件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 3日前 この投稿について報告する 🤠 Dallas! The future of connectivity is coming to Frisco. Ready to connect with the leaders driving network modernization right here in Texas? Join us for Cloudflare Immerse Dallas on February 12th! We’re bringing together the region’s top security, IT, and digital leaders for an afternoon of deep dives into the Connectivity Cloud, Zero Trust, and AI application security. It’s more than just sessions—it’s your chance to network with peers and get your toughest questions answered at our "Ask the Cloudflare Experts" bar. 📍 Where: HALL Park Hotel, Frisco, TX 📅 When: Thursday, Feb 12, 2026 | 1:30 PM - 5:00 PM (Happy Hour to follow! 🍹) Spots are limited. Secure your seat today! 👇 https://lnkd.in/dEKuBqve #CloudflareImmerse #DallasTech #NetSec #FriscoTX #Networking #CyberSecurity #ConnectivityCloud 50 4件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 4日前 この投稿について報告する What's your preferred method for knowledge sharing within a team (e.g., detailed READMEs, synchronous workshops, pairing)? #CloudflareChat 29 8件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 4日前 この投稿について報告する We are thrilled to announce that Cloudflare has been recognized as the current Company to Beat in the December 2025 Gartner AI Vendor Race for Edge Distribution Platform AI! Discover the key findings of the report from our article 👇 Cloudflare named as the current Company to Beat in a Gartner® report for Edge Distribution Platform AI! Cloudflare (LinkedInより) 657 11件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 5日前 編集済み この投稿について報告する Cloudflare is getting ready for ICE 2026 in Barcelona, taking place 19–21 January. We’ll be at Booth 4K30 sharing how Cloudflare for iGaming helps platforms deliver fast, secure, and reliable experiences for players around the world. If you’re attending, stop by to meet the team, explore our iGaming security solutions, and join us for a relaxed Happy Hour at the booth. If you pre-book a meeting with us, you’ll also be entered into a prize draw for a chance to win an exclusive FC Barcelona jersey on the first day of the event! Click here to book your meeting: https://lnkd.in/gSPe58K6 See you there! 33 いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 5日前 この投稿について報告する Is your organization struggling to manage a sprawling attack surface across hybrid environments? Join Cloudflare and Werner Executive VP & CIO Daragh Mahon to hear directly from one of our customers on their successful real-world Zero Trust deployments. Learn more about priority use cases, common challenges, and architectural strategies. Register today! https://lnkd.in/db4Gb6Rk #ZeroTrust #Cybersecurity #Cloudflare #Webinar 41 2件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 5日前 この投稿について報告する Defend against rising app-layer DDoS attacks 📱 In his latest article for theNET, Gregory Van den Top explains how DDoS attacks — often powered by AI — are a growing threat to applications. They can slow or completely crash software, bringing critical operations to a halt. The right strategic framework — focused on detecting, mitigating, and adapting — can help stop attacks and improve resilience: https://lnkd.in/dwuSqcm4 60 1件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 6日前 この投稿について報告する A BGP route leak in Venezuela recently impacted internet connectivity. Our latest analysis breaks down how this happened and why it highlights the need for better routing security across the global Internet. https://cfl.re/4qEaNQ5 A closer look at a BGP anomaly in Venezuela blog.cloudflare.com 358 4件のコメント いいね！ コメント シェア Cloudflare 1,123,490人のフォロワー 6日前 この投稿について報告する Cloudflare was proud to protect the Moldovan Central Election Commission during their elections. 🔗 Learn more about it on our blog: https://lnkd.in/gQ8P2NmB Anatolie Golovco 1週間前 CloudFlare mentioned Moldova in their 2025 Annual Impact Report. As a personal tip to web studios that care about protecting their customers against DDoS attacks: take a look at CloudFlare Pages, CloudFlare R2, and Hugo CMS as alternatives to traditional hosting setups and content management systems. https://lnkd.in/dxgycsYm #CloudFlare 41 2件のコメント いいね！ コメント シェア 今すぐ登録して新しい情報を確認しましょう Cloudflareで知り合いを見つけましょう おすすめの求人を閲覧しましょう すべての最新情報、ニュース、記事を閲覧しましょう メンバー登録 系列企業ページ Cloudflare for Public Sector コンピューター・ネットワークセキュリティ San Francisco、California Cloudflare Partner Network コンピューター・ネットワークセキュリティ 類似するページ Akamai Technologies 技術・情報・インターネット Cambridge、MA CrowdStrike コンピューター・ネットワークセキュリティ Palo Alto Networks コンピューター・ネットワークセキュリティ SANTA CLARA、California Atlassian ソフトウェア開発 Sydney、NSW Google ソフトウェア開発 Mountain View、CA Zscaler コンピューター・ネットワークセキュリティ San Jose、California Snowflake ソフトウェア開発 Microsoft ソフトウェア開発 Redmond、Washington Cisco ソフトウェア開発 San Jose、CA Databricks ソフトウェア開発 San Francisco、CA 類似するページをさらに表示 類似するページを部分表示 LinkedIn © 2026 会社概要 アクセシビリティ 利用規約 プライバシーポリシー Cookieポリシー 著作権ポリシー ブランドポリシー ゲスト向け管理ページ コミュニティガイドライン العربية (アラビア語) বাংলা (ベンガル語) Čeština (チェコ語) Dansk (デンマーク語) Deutsch (ドイツ語) Ελληνικά (ギリシャ語) English (英語) Español (スペイン語) فارسی (ペルシア語) Suomi (フィンランド語) Français (フランス語) हिंदी (ヒンディー語) Magyar (ハンガリー語) Bahasa Indonesia (インドネシア語) Italiano (イタリア語) עברית (ヘブライ語) 日本語 (日本語) 한국어 (韓国語) मराठी (マラーティー語) Bahasa Malaysia (マレー語) Nederlands (オランダ語) Norsk (ノルウェー語) ਪੰਜਾਬੀ (パンジャブ語) Polski (ポーランド語) Português (ポルトガル語) Română (ルーマニア語) Русский (ロシア語) Svenska (スウェーデン語) తెలుగు (テルグ語) ภาษาไทย (タイ語) Tagalog (タガログ語) Türkçe (トルコ語) Українська (ウクライナ語) Tiếng Việt (ベトナム語) 简体中文 (中国語 - 簡体字) 正體中文 (中国語 - 繁体字) 言語 同意してLinkedInに登録 登録またはサインインするために [続行] をクリックすることにより、LinkedInの 利用規約 、 プライバシーポリシー 、 Cookieポリシー に同意したものとみなされます。 サインインしてCloudflareの知り合いを見つけましょう サインイン ようこそ メールまたは携帯番号 パスワード 表示 パスワードをお忘れの場合 サインイン または 登録またはサインインするために [続行] をクリックすることにより、LinkedInの 利用規約 、 プライバシーポリシー 、 Cookieポリシー に同意したものとみなされます。 初めてご利用ですか? 今すぐ登録 または 初めてご利用ですか? 今すぐ登録 登録またはサインインするために [続行] をクリックすることにより、LinkedInの 利用規約 、 プライバシーポリシー 、 Cookieポリシー に同意したものとみなされます。 | 2026-01-13T09:29:16 |
http://git-scm.com/cheat-sheet#important-files | Git Cheat Sheet About Trademark Learn Book Cheat Sheet Videos External Links Tools Command Line GUIs Hosting Reference Install Community Table of Contents Getting Started Prepare to Commit Make Commits Move Between Branches Diff Staged/Unstaged Changes Diff Commits Ways to refer to a commit Discard Your Changes Edit History Code Archaeology Combine Diverged Branches Restore an Old File Add a Remote Push Your Changes Pull Changes Configure Git Important Files The entire Pro Git book written by Scott Chacon and Ben Straub is available to read online for free . Dead tree versions are available on Amazon.com . Git Cheat Sheet Getting Started Start a new repo: git init Clone an existing repo: git clone <url> Prepare to Commit Add untracked file or unstaged changes: git add <file> Add all untracked files and unstaged changes: git add . Choose which parts of a file to stage: git add -p Move file: git mv <old> <new> Delete file: git rm <file> Tell Git to forget about a file without deleting it: git rm --cached <file> Unstage one file: git reset <file> Unstage everything: git reset Check what you added: git status Make Commits Make a commit (and open text editor to write message): git commit Make a commit: git commit -m 'message' Commit all unstaged changes: git commit -am 'message' Move Between Branches Switch branches: git switch <name> OR git checkout <name> Create a branch: git switch -c <name> OR git checkout -b <name> List branches: git branch List branches by most recently committed to: git branch --sort=-committerdate Delete a branch: git branch -d <name> Force delete a branch: git branch -D <name> Diff Staged/Unstaged Changes Diff all staged and unstaged changes: git diff HEAD Diff just staged changes: git diff --staged Diff just unstaged changes: git diff Diff Commits Show diff between a commit and its parent: git show <commit> Diff two commits: git diff <commit> <commit> Diff one file since a commit: git diff <commit> <file> Show a summary of a diff: git diff <commit> --stat git show <commit> --stat Ways to refer to a commit Every time we say <commit> , you can use any of these: a branch main a tag v0.1 a commit ID 3e887ab a remote branch origin/main current commit HEAD 3 commits ago HEAD^^^ or HEAD~3 Discard Your Changes Delete unstaged changes to one file: git restore <file> OR git checkout <file> Delete all staged and unstaged changes to one file: git restore --staged --worktree <file> OR git checkout HEAD <file> Delete all staged and unstaged changes: git reset --hard Delete untracked files: git clean 'Stash' all staged and unstaged changes: git stash Edit History "Undo" the most recent commit (keep your working directory the same): git reset HEAD^ Squash the last 5 commits into one: git rebase -i HEAD~6 Then change "pick" to "fixup" for any commit you want to combine with the previous one Undo a failed rebase: git reflog BRANCHNAME Then manually find the right commit ID in the reflog, then run: git reset --hard <commit> Change a commit message (or add a file you forgot): git commit --amend Code Archaeology Look at a branch's history: git log main git log --graph main git log --oneline Show every commit that modified a file: git log <file> Show every commit that modified a file, including before it was renamed: git log --follow <file> Find every commit that added or removed some text: git log -G banana Show who last changed each line of a file: git blame <file> Combine Diverged Branches Combine with rebase: git switch banana git rebase main Before: After: Combine with merge: git switch main git merge banana Before: After: Combine with squash merge: git switch main git merge --squash banana git commit Before: After: Bring a branch up to date with another branch (aka "fast-forward merge"): git switch main git merge banana Before: After: Copy one commit onto the current branch: git cherry-pick <commit> Before: After: Restore an Old File Get the version of a file from another commit: git checkout <commit> <file> OR git restore <file> --source <commit> Add a Remote git remote add <name> <url> Push Your Changes Push the main branch to the remote origin : git push origin main Push the current branch to its remote "tracking branch": git push Push a branch that you've never pushed before: git push -u origin <name> Force push: git push --force-with-lease Push tags: git push --tags Pull Changes Fetch changes (but don't change any of your local branches): git fetch origin main Fetch changes and then rebase your current branch: git pull --rebase Fetch changes and then merge them into your current branch: git pull origin main OR git pull Configure Git Set a config option: git config user.name 'Your Name' Set option globally: git config --global ... Add an alias: git config alias.st status See all possible config options: man git-config Important Files Local git config: .git/config Global git config: ~/.gitconfig List of files to ignore: .gitignore About this site Patches, suggestions, and comments are welcome. Git is a member of Software Freedom Conservancy | 2026-01-13T09:29:16 |
https://www.linkedin.com/login?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2Fted-conferences&fromSignIn=true&trk=organization_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/categories/online-form-builder-software | Best Online Form Builder Software | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Operations Manager (4) Owner (3) Project Manager (3) Information Technology Manager (3) Software Engineer (3) See all products Find top products in Online Form Builder Software category Software used to create, share, and manage online forms. - Use drag-and-drop interfaces and templates to create forms - Collect and view responses, manage payments, and automate workflows - Embed forms in a website or share directly with an audience 157 results Zoho Forms Online Form Builder Software by Zoho Simplify your data collection process with Zoho Forms' intuitive online form builder. Our no-code, feature-rich platform seamlessly integrates with multiple applications, enabling effortless data management across your business operations. View product Jotform Online Form Builder Software by Jotform Jotform is the easiest online form builder, letting you create custom forms and surveys to collect contact info, payments, signatures, files, and more. Use our drag-and-drop form builder to make your own form from scratch or customize one of 10,000+ free templates to meet your exact needs — no coding required! Power up your forms and surveys with advanced form fields, widgets, and 100+ third-party integrations designed to help you do more with your data. Publish your form by embedding it in your website or by sharing a link — and watch as submissions arrive instantly! You can even assign forms to teammates for seamless online collaboration. Track and manage submissions and turn them into PDFs, reports, or approval flows automatically. Jotform also ensures the privacy of your data, offering top-notch security via 256 bit SSL, form encryption, PCI and GDPR compliance, and optional HIPAA compliance. Simplify online data collection and streamline your workflow with Jotform. View product Typeform Online Form Builder Software by Typeform People-friendly forms, quizzes, and surveys—designed to stand out. View product Tally Online Form Builder Software by Tally Create forms for all purposes in seconds. Without knowing how to code, and for free! View product Jotform Enterprise Online Form Builder Software by Jotform Jotform Enterprise gives leaders of businesses, institutions, government agencies, and nonprofits unlimited access to its suite of powerful no-code solutions, including forms, tables, apps, reports, and more to optimize efficiency, security, and workflows. Jotform Enterprise features white labeling for custom domains, dedicated servers, multiuser teams with admin-level controls, single sign-on, and a dedicated support team to answer any questions about our no-code, drag-and-drop, user-friendly interface. Jotform maintains the highest industry standards for security with 256-bit SSL connections, form encryption, GDPR compliance, geolocalization of data, PCI DSS Level 1 compliance, California Consumer Privacy Act (CCPA) compliance, HIPAA compliance, and Business Associate Agreements (BAAs) available upon request. As a StateRAMP progressing product with over 400 apps, integrations, and custom apps through our API, it’s easy to plug into your existing systems. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights Jotform Mobile Forms Online Form Builder Software by Jotform Jotform Mobile Forms, the free mobile app for iOS and Android, lets you access your forms and surveys from any device to collect data, payments, files, and more on the go — even offline! Fill out your forms and view submissions without accessing a computer. You get all the powerful features of Jotform at your fingertips, including advanced features like QR codes, a Take Photo field, and the ability to capture information like GPS location, voice recordings, e-signatures, file uploads, and more. With kiosk mode, you can collect multiple responses through a form that refreshes automatically upon submission — perfect for collecting registrations, feedback, and more on your smartphone or tablet at trade shows or conferences. You can even collect data offline. It will automatically sync to your Jotform account once you’re reconnected. View product Forms Made Easy Online Form Builder Software by HIC Global Solutions Forms Made Easy helps users to create Smarter Forms, Collect Better Data View product Wufoo Online Form Builder Software by SurveyMonkey Wufoo's online form builder helps you create custom HTML forms without writing code. Use our online form creator to build contact forms, surveys, event registrations, and more. Sign up free! View product EngageForm Online Form Builder Software by Codiant - A YASH Technologies Company EngageForm is an AI-powered form builder that lets users create smart, logic-driven surveys using natural language prompts. Designed for non-technical teams, it supports real-time previews, drag-and-drop editing, analytics, and multi-channel sharing - making form creation faster, more intuitive, and tailored for HR, marketing, education, healthcare, and SaaS use cases. View product GoCanvas Online Form Builder Software by GoCanvas Built just for your business, GoCanvas has thousands of mobile form apps to help you save time and money on data collection. Leave paper forms behind with GoCanvas. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?modality=modality%3Atimeseries | Time-series Datasets – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":31300,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities Reset Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 31,300 Full-text search Edit filters Sort: Trending Active filters: timeseries Clear all 123olp/binance-futures-ohlcv-2018-2026 Viewer • Updated 2 days ago • 425M • 478 • 96 facebook/jepa-wms Viewer • Updated 11 days ago • 524 • 159 • 7 youliangtan/so101-table-cleanup Viewer • Updated Jun 6, 2025 • 47k • 1.4k • 23 IntelLabs/Intel_Robotic_Welding_Multimodal_Dataset Updated Sep 23, 2025 • 23 • 15 Datadog/BOOM Preview • Updated Sep 8, 2025 • 3.44k • 30 lerobot/libero Viewer • Updated 22 days ago • 275k • 3.21k • 4 G3ND3K/so101_picking_up_green_lego_big Viewer • Updated 11 days ago • 32.9k • 73 • 5 webxos/snipercell_RL Viewer • Updated 3 days ago • 1 • 61 • 2 Chafinch/COF10 Viewer • Updated 5 days ago • 1.54k • 24 • 2 Salesforce/lotsa_data Viewer • Updated Jan 21, 2025 • 3.97M • 16.2k • 92 lerobot/pusht Viewer • Updated Sep 27, 2025 • 25.7k • 6.28k • 30 lerobot/aloha_sim_insertion_scripted Viewer • Updated Sep 27, 2025 • 20k • 2.67k • 3 lerobot/aloha_mobile_cabinet Viewer • Updated Oct 23, 2025 • 128k • 2.38k • 8 Cohere/msmarco-v2.1-embed-english-v3 Viewer • Updated Aug 5, 2024 • 53.2M • 1.26k • 3 Metacreation/GigaMIDI Viewer • Updated Dec 12, 2025 • 3.44M • 400 • 25 Salesforce/GiftEvalPretrain Preview • Updated Jan 21, 2025 • 567k • 22 MagicLuke/MyST Viewer • Updated Jul 5, 2025 • 714k • 49 • 3 physical-intelligence/libero Viewer • Updated Feb 2, 2025 • 273k • 21.5k • 56 unitreerobotics/G1_Dex3_ObjectPlacement_Dataset Viewer • Updated Sep 16, 2025 • 98.3k • 920 • 4 autogluon/fev_datasets Viewer • Updated Oct 1, 2025 • 128k • 9.2k • 5 nvidia/PhysicalAI-Robotics-Manipulation-Kitchen Viewer • Updated May 15, 2025 • 405k • 4.64k • 11 tahoebio/Tahoe-100M Viewer • Updated Jul 23, 2025 • 4.29B • 19.6k • 94 nvidia/PhysicalAI-Robotics-Manipulation-Objects Viewer • Updated May 15, 2025 • 130k • 4k • 6 jesbu1/libero_90_lerobot Viewer • Updated Mar 17, 2025 • 575k • 2.62k • 2 mhyatt000/sim_stack Viewer • Updated Apr 27, 2025 • 220k • 813 • 1 lerobot/svla_so100_stacking Viewer • Updated Oct 22, 2025 • 23k • 624 • 3 lerobot/svla_so100_sorting Viewer • Updated Oct 22, 2025 • 35.7k • 575 • 10 ZibinDong/libero_spatial Viewer • Updated Jun 10, 2025 • 62.3k • 860 • 1 RoboHP/metaworld_mt50_v3_50d_512r Viewer • Updated Jul 3, 2025 • 187k • 1.97k • 1 IPEC-COMMUNITY/libero_spatial_no_noops_1.0.0_lerobot Viewer • Updated Nov 3, 2025 • 53k • 3.53k • 2 Previous 1 2 3 ... 100 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://docs.fuse.io/developers/fusebox/sdk/installation-and-setup | Installation And Setup | Fuse Documentation Skip to main content Basics Developers Search Building On Fuse Web3 tools Tutorials Subgraphs FuseBox SDK Installation And Setup Create Smart Contract Wallet Send Native/ERC20 Transactions Send Batch Transactions Non-Blocking Transactions Transfer NFT Swap Tokens GET List of Tokens Owned by Address GET Historical Transactions GET Token Details GET Smart Wallet Token Balance GET Staking Options Stake and Unstake Tokens GET Staked Tokens GET Token Price GET Token Price Change in the Last 24 hours GET the Price Change in Interval GET the list of Supported Tokens Sponsored Transactions Migration from Old Versions Limitations Troubleshooting APIs Architecture Charge FuseBox SDK Installation And Setup On this page Installation And Setup Installation Web Flutter npm Yarn Bun pnpm npm install @fuseio/fusebox-web-sdk yarn add @fuseio/fusebox-web-sdk bun add @fuseio/fusebox-web-sdk pnpm add @fuseio/fusebox-web-sdk Install the FuseSDK using Dart or flutter. dart pub add fuse_wallet_sdk flutter pub add fuse_wallet_sdk Once you have installed the package, you can import it into your code: Web Flutter import { FuseSDK } from "@fuseio/fusebox-web-sdk" ; import 'package:fuse_wallet_sdk/fuse_wallet_sdk.dart' ; Usage To use the SDK in your project, you must create an instance of the FuseSDK class. This class is the key to interacting with the Fuse API using the SDK. Fortunately, the FuseSDK class provides a range of instance methods, allowing you to execute various operations with the API. Whether you aim to fetch or create a smart wallet, relay an ERC20/FUSE transfer, relay an ERC721 transfer, relay a generic transaction, swap tokens, or stake tokens, the FuseSDK class has you covered. Additionally, the SDK provides data features that allow you to get the list of tokens owned by an address, get token details, and get a smart wallet's token balance. The following code initializes the Fuse SDK and creates an instance of the FuseSDK class. The apiKey variable should be set to your own API key. Web Flutter import { ethers } from "ethers" ; import { FuseSDK } from "@fuseio/fusebox-web-sdk" ; const apiKey = "API_KEY" ; const credentials = new ethers . Wallet ( "PRIVATE_KEY" ) ; const fuseSDK = await FuseSDK . init ( apiKey , credentials ) ; import 'package:fuse_wallet_sdk/fuse_wallet_sdk.dart' ; final apiKey = 'API_KEY' ; final privateKey = EthPrivateKey . fromHex ( 'YOUR_PRIVATE_KEY' ) ; final fuseSDK = await FuseSDK . init ( apiKey , privateKey ) ; Once you have created an instance of the FuseSDK class, you can use its instance methods to interact with the Fuse API. In the following section, we will cover the available methods of the SDK. Edit this page Previous SDK Next Create Smart Contract Wallet Installation Usage Youtube GitHub Twitter Telegram Discord Forum Getting Started Fuse Network Mobile Stack Voltage Finance Under the hood Explorer Bridge Staking Governance Service Status General Brand kits Jobs Subscribe to Newsletter © 2025 Fuse. All Rights Reserved | 2026-01-13T09:29:16 |
http://git-scm.com/cheat-sheet#pull-changes | Git Cheat Sheet About Trademark Learn Book Cheat Sheet Videos External Links Tools Command Line GUIs Hosting Reference Install Community Table of Contents Getting Started Prepare to Commit Make Commits Move Between Branches Diff Staged/Unstaged Changes Diff Commits Ways to refer to a commit Discard Your Changes Edit History Code Archaeology Combine Diverged Branches Restore an Old File Add a Remote Push Your Changes Pull Changes Configure Git Important Files The entire Pro Git book written by Scott Chacon and Ben Straub is available to read online for free . Dead tree versions are available on Amazon.com . Git Cheat Sheet Getting Started Start a new repo: git init Clone an existing repo: git clone <url> Prepare to Commit Add untracked file or unstaged changes: git add <file> Add all untracked files and unstaged changes: git add . Choose which parts of a file to stage: git add -p Move file: git mv <old> <new> Delete file: git rm <file> Tell Git to forget about a file without deleting it: git rm --cached <file> Unstage one file: git reset <file> Unstage everything: git reset Check what you added: git status Make Commits Make a commit (and open text editor to write message): git commit Make a commit: git commit -m 'message' Commit all unstaged changes: git commit -am 'message' Move Between Branches Switch branches: git switch <name> OR git checkout <name> Create a branch: git switch -c <name> OR git checkout -b <name> List branches: git branch List branches by most recently committed to: git branch --sort=-committerdate Delete a branch: git branch -d <name> Force delete a branch: git branch -D <name> Diff Staged/Unstaged Changes Diff all staged and unstaged changes: git diff HEAD Diff just staged changes: git diff --staged Diff just unstaged changes: git diff Diff Commits Show diff between a commit and its parent: git show <commit> Diff two commits: git diff <commit> <commit> Diff one file since a commit: git diff <commit> <file> Show a summary of a diff: git diff <commit> --stat git show <commit> --stat Ways to refer to a commit Every time we say <commit> , you can use any of these: a branch main a tag v0.1 a commit ID 3e887ab a remote branch origin/main current commit HEAD 3 commits ago HEAD^^^ or HEAD~3 Discard Your Changes Delete unstaged changes to one file: git restore <file> OR git checkout <file> Delete all staged and unstaged changes to one file: git restore --staged --worktree <file> OR git checkout HEAD <file> Delete all staged and unstaged changes: git reset --hard Delete untracked files: git clean 'Stash' all staged and unstaged changes: git stash Edit History "Undo" the most recent commit (keep your working directory the same): git reset HEAD^ Squash the last 5 commits into one: git rebase -i HEAD~6 Then change "pick" to "fixup" for any commit you want to combine with the previous one Undo a failed rebase: git reflog BRANCHNAME Then manually find the right commit ID in the reflog, then run: git reset --hard <commit> Change a commit message (or add a file you forgot): git commit --amend Code Archaeology Look at a branch's history: git log main git log --graph main git log --oneline Show every commit that modified a file: git log <file> Show every commit that modified a file, including before it was renamed: git log --follow <file> Find every commit that added or removed some text: git log -G banana Show who last changed each line of a file: git blame <file> Combine Diverged Branches Combine with rebase: git switch banana git rebase main Before: After: Combine with merge: git switch main git merge banana Before: After: Combine with squash merge: git switch main git merge --squash banana git commit Before: After: Bring a branch up to date with another branch (aka "fast-forward merge"): git switch main git merge banana Before: After: Copy one commit onto the current branch: git cherry-pick <commit> Before: After: Restore an Old File Get the version of a file from another commit: git checkout <commit> <file> OR git restore <file> --source <commit> Add a Remote git remote add <name> <url> Push Your Changes Push the main branch to the remote origin : git push origin main Push the current branch to its remote "tracking branch": git push Push a branch that you've never pushed before: git push -u origin <name> Force push: git push --force-with-lease Push tags: git push --tags Pull Changes Fetch changes (but don't change any of your local branches): git fetch origin main Fetch changes and then rebase your current branch: git pull --rebase Fetch changes and then merge them into your current branch: git pull origin main OR git pull Configure Git Set a config option: git config user.name 'Your Name' Set option globally: git config --global ... Add an alias: git config alias.st status See all possible config options: man git-config Important Files Local git config: .git/config Global git config: ~/.gitconfig List of files to ignore: .gitignore About this site Patches, suggestions, and comments are welcome. Git is a member of Software Freedom Conservancy | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/kaspersky-industrial-cybersecurity/ | Kaspersky Industrial Cybersecurity | LinkedIn Skip to main content LinkedIn Kaspersky in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Kaspersky Industrial Cybersecurity Enterprise Architecture Software by Kaspersky See who's skilled in this Add as skill Learn more Report this product About Native Extended Detection and Response (XDR) platform for critical infrastructure protection. The core of the OT cybersecurity ecosystem. Media Products media viewer No more previous content How to make life of industrial IT manager much easier Join us as we uncover the intricacies of Condor Carpets' journey towards enhanced cybersecurity and operational efficiency with Kaspersky solutions. We'll explore the challenges they faced, the implementation process, and the remarkable benefits reaped by Condor Carpets after integrating Kaspersky Industrial CyberSecurity into their infrastructure. Find out more about Kaspersky Industrial CyberSecurity: https://kas.pr/6zf3 No more next content Similar products Cameo Enterprise Architecture Cameo Enterprise Architecture Enterprise Architecture Software CAST Highlight CAST Highlight Enterprise Architecture Software ABACUS ABACUS Enterprise Architecture Software Ardoq Ardoq Enterprise Architecture Software Enterprise Architecture Enterprise Architecture Enterprise Architecture Software Bizzdesign Enterprise Architecture Management (EAM) Bizzdesign Enterprise Architecture Management (EAM) Enterprise Architecture Software Sign in to see more Show more Show less Kaspersky products Kaspersky Container Security Kaspersky Container Security Container Security Software Kaspersky Digital Footprint Intelligence Kaspersky Digital Footprint Intelligence Digital Forensics Software Kaspersky Next Kaspersky Next Endpoint Detection & Response (EDR) Software Kaspersky Password Manager Kaspersky Password Manager Password Management Software Kaspersky Premium Kaspersky Premium Antivirus Software Kaspersky Safe Kids Kaspersky Safe Kids Antivirus Software Kaspersky Threat Intelligence Kaspersky Threat Intelligence Threat Intelligence Platforms Kaspersky VPN Kaspersky VPN Virtual Private Network (VPN) Software KasperskyOS KasperskyOS Operating Systems Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/company/propublica?trk=products_details_guest_organization_image | ProPublica | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join now ProPublica Media Production New York, New York 72,236 followers Journalism in the public interest. And no, we're not shutting up. See jobs Follow Discover all 254 employees Report this company About us ProPublica is an independent, nonprofit newsroom that produces investigative journalism with moral force. We dig deep into important issues, shining a light on abuses of power and betrayals of public trust — and we stick with those issues as long as it takes to hold power to account. With a team of more than 75 dedicated journalists, ProPublica covers a range of topics including government and politics, business, criminal justice, the environment, education, health care, immigration, and technology. We focus on stories with the potential to spur real-world impact. Among other positive changes, our reporting has contributed to the passage of new laws; reversals of harmful policies and practices; and accountability for leaders at local, state and national levels. Investigative journalism requires a great deal of time and resources, and many newsrooms can no longer afford to take on this kind of deep-dive reporting. As a nonprofit, ProPublica’s work is powered primarily through donations. The vast bulk of the money we spend goes directly into world-class, award-winning journalism. We are committed to uncovering the truth, no matter how long it takes or how much it costs, and we practice transparent financial reporting so donors know how their dollars are spent. ProPublica was founded in 2007-2008 with the belief that investigative journalism is critical to our democracy. Our staff remains dedicated to carrying forward the important work of exposing corruption, informing the public about complex issues, and using the power of investigative journalism to spur reform. Website https://www.propublica.org External link for ProPublica Industry Media Production Company size 51-200 employees Headquarters New York, New York Type Nonprofit Founded 2008 Locations Primary 155 Ave of the Americas 13th Floor New York, New York 10013, US Get directions Employees at ProPublica Ben Werdmuller Rui Kaneya Tyson Evans Audrey Dutton See all employees Updates ProPublica 72,236 followers 9h Report this post In July 2025, we documented nearly 50 incidents of immigration officers shattering car windows to make arrests — a tactic experts say was rarely used before Trump took office. ICE claims its officers use a “minimum amount of force.” You can judge for yourself: https://propub.li/4pvjmf7 56 2 Comments Like Comment Share ProPublica reposted this Cengiz Yar 17h Report this post Our three-part investigation into public lands ranching explores the subsidies baked into ranching, environmental impacts, and politics working behind the scenes. Here are the biggest takeaways from Jimmy Tobias & Mark Olalde's collaborative project for ProPublica & High Country News . https://lnkd.in/gjDSR5NY The Biggest Takeaways From Our Investigation Into Grazing on Public Lands https://www.propublica.org 15 1 Comment Like Comment Share ProPublica reposted this Lucas Waldron 13h Report this post Collab with Heather Vogell + Agnel Philip . We analyzed what happened when SpaceX's starship rocket exploded last year and found 21 flights that made sudden turns to exit or avoid the debris. The repeated explosions have made pilots and passengers unwitting participants in SpaceX’s test of the most powerful rocket ever built. Read the story on ProPublica : https://lnkd.in/gvpqajqC 14 1 Comment Like Comment Share ProPublica 72,236 followers 15h Report this post As President Donald Trump’s administration pushes a pro-ranching agenda, ProPublica and High Country News investigated how public lands grazing has evolved. Here are the biggest takeaways from our reporting: https://propub.li/4qiFdYw 10 Like Comment Share ProPublica 72,236 followers 1d Report this post Under a zero tolerance policy, the first Trump administration separated immigrant children from their families at the U.S.-Mexico border. New data suggests separations now happen all over the country, often after little more than a traffic stop. Read the full story (published Nov. 2025): https://propub.li/49pLImt 84 2 Comments Like Comment Share ProPublica 72,236 followers 1d Report this post 18 years ago, we started ProPublica to do hard-hitting, rigorous journalism that exposes wrongdoing and injustice. If you have a tip related to the Trump administration, we want to hear it. Here's how to contact our reporters securely: propublica.org/tips 63 Like Comment Share ProPublica 72,236 followers 2d Report this post We found more than two dozen cases of immigration agents using "less lethal" weapons in ways that appear to flout the government's own rules, including by aiming at someone’s head, spine or groin or deploying chemical agents near children. Read more (published Nov. 2025): https://propub.li/4jCTg8L 164 16 Comments Like Comment Share ProPublica 72,236 followers 2d Report this post Americans have been dragged, tackled, beaten, tased and shot by immigration agents. They’ve had their necks kneeled on. They’ve been held outside in the rain while in their underwear. At least three citizens were pregnant when agents detained them. Revisit our story from Oct. 2025: https://propub.li/3N5UFIT 414 35 Comments Like Comment Share ProPublica 72,236 followers 3d Report this post WATCH: More than 80% of U.S. children attend public schools. Some of the Education Department’s ultraconservative advisers, led by Secretary Linda McMahon, want to change that. Here’s an inside look at their dismantling of public education: …more Inside the Trump Administration’s Plan to Change Public Education https://www.youtube.com/ 17 3 Comments Like Comment Share ProPublica reposted this Max Blau 3d Report this post A new lawsuit alleges that an insurer’s ghost network hindered New York City employees from accessing the mental health care they sought — and harmed the reputation of psychiatrists wrongly listed as being in-network. The lawsuit cites ProPublica 's reporting on provider directory errors and how insurers have driven mental health providers to quit their networks. You can read this story — and all of our past coverage on the ways insurers interfere with mental health care benefits — in the links I've dropped in the comments. 69 6 Comments Like Comment Share Join now to see what you are missing Find people you know at ProPublica Browse recommended jobs for you View all updates, news, and articles Join now Similar pages The Associated Press Media Production New York, NY NPR Broadcast Media Production and Distribution Washington, DC Journalism and Media Opportunities Broadcast Media Production and Distribution The Marshall Project Online Audio and Video Media New York, NY The New York Times Newspaper Publishing New York, NY Vox Media Online Audio and Video Media Washington, DC The Atlantic Book and Periodical Publishing Washington, District of Columbia Reuters Media Production New York, New York POLITICO Online Audio and Video Media Arlington, Virginia The New Yorker Book and Periodical Publishing New York, NY Show more similar pages Show fewer similar pages Browse jobs Journalist jobs 19,421 open jobs Reporter jobs 24,186 open jobs Writer jobs 26,384 open jobs Editor jobs 19,020 open jobs Freelance Journalist jobs 11,021 open jobs Producer jobs 102,690 open jobs Project Manager jobs 253,048 open jobs Editorial Assistant jobs 43,732 open jobs Executive jobs 690,514 open jobs Associate jobs 1,091,945 open jobs Vice President Communications jobs 3,081 open jobs Marketing Manager jobs 106,879 open jobs Analyst jobs 694,057 open jobs Marketing Specialist jobs 49,178 open jobs Assistant jobs 711,811 open jobs Video Producer jobs 4,569 open jobs Copywriter jobs 17,206 open jobs Coordinator jobs 545,033 open jobs Manager jobs 1,880,925 open jobs Editorial Intern jobs 1,236 open jobs Show more jobs like this Show fewer jobs like this Funding ProPublica 4 total rounds Last Round Grant Feb 28, 2020 External Crunchbase Link for last round of funding US$ 1.0M Investors Craig Newmark Philanthropies See more info on crunchbase More searches More searches Journalist jobs Editor jobs Writer jobs Reporter jobs Producer jobs Analyst jobs Engineer jobs Business Administrator jobs Teacher jobs Senior Sales Marketing Manager jobs Executive Editor jobs Assistant jobs Conference Event Coordinator jobs Photo Editor jobs Program Coordinator jobs Inspector General jobs Assistant Editor jobs Executive Director jobs Multimedia Journalist jobs Communications Specialist jobs Executive jobs Curator jobs Photojournalist jobs Knowledge Management Specialist jobs Communications Coordinator jobs Senior Editor jobs Graphic Artist jobs News Producer jobs Editorial Assistant jobs Executive Assistant jobs Video Producer jobs Designer jobs Grants Writer jobs Marketing Specialist jobs Voice Over Artist jobs Press Secretary jobs Paralegal jobs Attorney jobs Product Manager jobs Policy Analyst jobs Hiring Manager jobs Real Estate Analyst jobs Operations Assistant jobs Compliance Specialist jobs Manager jobs Coordinator jobs Research Assistant jobs Associate jobs Operations Coordinator jobs Project Manager jobs Director jobs Communication Trainee jobs Community Sales Manager jobs Project Management Specialist jobs Copywriter jobs Operator jobs Reader jobs Researcher jobs Content Specialist jobs Media Planner jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at ProPublica Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://www.linkedin.com/company/kaltura/?trk=products_details_guest_organization_page | Kaltura | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join for free Kaltura Software Development Our Video Experience Cloud drives virtual events, communication, learning, & TV experiences for millions of users daily. See jobs Follow View all 740 employees Report this company Overview Jobs Life About us Kaltura’s mission is to power any video experience for any organization. Kaltura is the leading video cloud, powering the broadest range of video experiences. Our Video Experience Cloud is used by leading brands reaching millions of users, at home, at school, and at work, for virtual events, communication, collaboration, training, marketing, sales, customer care, teaching, learning, and entertainment experiences. Website http://corp.kaltura.com External link for Kaltura Industry Software Development Company size 501-1,000 employees Headquarters Remote First Type Public Company Founded 2006 Specialties video platform, video management, video publishing, video streaming, interactive video, media management, media distribution, video portals, video players, video solutions, online video, mobile video, video conferencing, video communication, online meetings, meeting solutions, webinars, townhalls, lecture capture, cloud tv, OTT TV, video cloud, video platform as a service, media services, vpaas, podcasting, video messaging, virtual events, hybrid events, event platform, training platform, and webinars Products Kaltura AI Video Experience Cloud Kaltura AI Video Experience Cloud Live Streaming Software Driving virtual events, communication, learning, and TV experiences for millions of users daily. Locations Primary Remote First, US Get directions 860 Broadway New York, NY 10003, US Get directions Shoham 2 Ramat Gan, Israel 00000, IL Get directions 201 Mission St. San Francisco, CA 94105, US Get directions 303-306 High Holborn Northumberland House 4th Floor London, WC1V 7JZ, GB Get directions Show more locations Show fewer locations Employees at Kaltura Eynav (Navi) Azaria David Rosenbaum Ron Yekutiel Amir Chervinsky See all employees Updates Kaltura 83,404 followers 22h Report this post 🧘♀️ When content workflows finally take a breath. Most “AI tools” still ask people to stay involved at every step. Agentic AI changes that by handling the complexity for you. It understands rules, manages dependencies, and runs multi step publishing workflows quietly in the background, with minimal supervision. In this webinar, Sagi Bettan and Robyn Hall will show how the Publishing Agent moves AI from generative to executive. You will see how teams can automate publishing, scale accessibility, and apply governance with confidence, while freeing people to focus on higher value work. 📅 January 14 🕚 11:00 EST | 17:00 CET Join us to see how publishing workflows can run smoothly, without constant hands on control.👇 https://lnkd.in/d66BC5gX #AI #AgenticAI #ContentAutomation #VideoWorkflow #EnterpriseVideo …more 8 Like Comment Share Kaltura 83,404 followers 4d Report this post ✨🤝☁️ Where video, AI, and cloud strategy meet. As part of our ongoing partnership with Amazon Web Services (AWS) , Kaltura’s Strategic Account Executive Gonzalo Wynter sat down with AWS’s Stuart Lepkowsky for a conversation about what’s shaping the future of enterprise video. They dive into AI-powered video experiences, scalable cloud strategy, and how Kaltura and AWS are helping organizations elevate both customer and employee engagement at scale. If you’re interested in real-world AI, enterprise video innovation, and what’s coming next, this one’s worth watching. Watch the full interview (link in the comments👇) #AI #EnterpriseVideo #DigitalTransformation #StrategicPartnerships …more 43 1 Comment Like Comment Share Kaltura 83,404 followers 5d Edited Report this post 🤖 AI is about to become part of the workforce. For real. According to Kaltura's CTO, Alan Bekker, PhD , this is what the near future looks like: The world’s largest enterprises running purpose built avatars across marketing, sales, customer service, HR, onboarding, and IT. Not demos. Not experiments. Fully available, multilingual, 24/7 AI agents that answer questions, support customers, sell products, and educate users at scale. This is how companies expand their workforce without expanding headcount. And this is where real time avatars and agentic AI are heading next. ▶️ Watch the clip to hear his vision. Try Kaltura’s Real Time Avatars: 👇 https://lnkd.in/dAm4wRyq #AI #AgenticAI #FutureOfWork #AIAvatars …more 35 1 Comment Like Comment Share Kaltura 83,404 followers 6d Report this post 🚫🍼 Stop babysitting content. Meet the Publishing Agent. Most “AI tools” still depend on humans to manage every step. Agentic AI changes that, introducing systems that understand rules, follow dependencies, and execute multi step publishing workflows with minimal supervision. In this webinar, Sagi Bettan , Product Manager at Kaltura, and Robyn Hall , Content Marketing Manager at Kaltura, will show how the Publishing Agent moves AI from generative to executive, helping teams automate publishing, scale accessibility, and apply governance with confidence. 📅 January 14 🕚 11:00 EST | 17:00 CET 👉 Join us to see how to push the pedal on publishing workflows: https://lnkd.in/d66BC5gX #AI #AgenticAI #ContentAutomation #VideoWorkflow #EnterpriseVideo …more 21 2 Comments Like Comment Share Kaltura 83,404 followers 2w Report this post 🧑🎄🧞♂️ This holiday season has been more immersive than ever, here at Kaltura! Many Kalturians, including our CPO, Eynav (Navi) Azaria , are already exploring new possibilities. With Kaltura's Immersive Agents, video becomes a living interface. Users can ask questions, explore ideas, and get instant, personalized guidance, all delivered through a real-time interactive avatar. Want to experience it firsthand? You can ask Navi’s avatar more about our latest products: https://lnkd.in/dJCnGwNM #HappyHolidays #MerryChristmas #AIAvatars #DigitalAvatars Eynav (Navi) Azaria 2w For years, video has been one-way. We’re changing that. With Kaltura Immersive Agents, video becomes a living interface: ask, explore, and get instant, personalized guidance, delivered through a real-time interactive avatar. Want to experience it firsthand? Speak with my avatar here: https://lnkd.in/dmh4t-hc 6 Like Comment Share Kaltura 83,404 followers 2w Report this post Big things are coming in 2026! Smarter screens. Smarter stories. Smarter workflows. For now, it’s time to pause, recharge, and enjoy the season. Merry Christmas and Happy Holidays 🎁✨ #HappyHolidays #MerryChristmas #AIAvatars #DigitalAvatars #AIIsTheNewUI …more 19 Like Comment Share Kaltura 83,404 followers 3w Edited Report this post 🚀📈 Love seeing our TV customers win! 26% year over year growth in users, service stability above 99.95%, and accessibility features that are making a real impact for viewers. All powered by Kaltura’s super aggregation capabilities, bringing together content from Netflix, HBO, Voyo, and more into one seamless TV experience. Big congrats to the O2 Slovakia team. Proud to be part of the journey. ✨ #CustomerSuccess #StreamingInnovation #VideoTech #Accessibility #OTT #SuperAggregation #ProudPartner Stanislav Mikulič 3w Edited Rok 2025 v O2 TV? Poriadna jazda! 📈 Rastieme: #O2TV medziročne vyskočila o 26 %. Teší ma, že vás náš obsah baví čoraz viac! 📺 Viac obsahu: Do jednoduchej a prehľadnej ponuky sme starostlivo vybrali 12 nových kanálov. Okrem toho sme vyladili Maďarský balík, ktorý má dnes už 10 kvalitných staníc. ⚡ Najvýkonejší Set-Top box na trhu: V auguste sme nasadili jeden z najpokročilejších STB na svete. KAON ATV1970 od KAON GROUP & display unit je rýchlik s Amlogic X5M AI chipom, ktorý zlepšuje kvalitu obrazu a videa. Spolu s Android TV 14, Wi-Fi 6 a Dolby Vision urobí aj z obyčajnej telky kino. Nechýba v ňom ani obľúbený #Netflix , #VOYO alebo #HBO Max. ✅ Spoľahlivosť na prvom mieste: Naším cieľom je, aby ste pozerali dokonale agregovaný obsah bez prerušenia. Tento rok sme udržali stabilitu a dostupnosť služby na úrovni vyše 99,95 % a klúčové performance KPI sme medziročne zlepšili o 22 %. 🙏🏻 CETIN & Kaltura ♿ TV pre každého: Vďaka zmenám v aplikáciách a UI sme vylepšili funkcie prístupnosti. Či už ide o ovládanie alebo intuitívne prostredie, chceme, aby si obsah užil každý, bez bariér. 🥂 Vstup do roku 2026 bude o to zaujímavejší vďaka novým partnerstvám a výzvam. Vďaka všetkým, ktorí ste v tom s nami! 21 2 Comments Like Comment Share Kaltura 83,404 followers 3w Report this post This is probably the last time you’ll see these three quiet. 🤐 🤐 🤐 AI is everywhere in marketing, but impact isn’t. Nearly every team uses AI, yet only a tiny fraction has it fully integrated. Add content overload, scattered data, and slow processes, and it’s clear why so many marketers feel the playbook is breaking. In this session, Eran Amit (Senior Director of Digital Marketing), Noa Fenigstein (Director of Content Marketing), and Idan (Stacy) Jakobovich (Senior Creative Director) will share what a full year of data taught us — the wins, the misses, and the trends shaping 2026. They’ll break down: 💡 What 300 plus marketing leaders revealed about personalization and data gaps 💡 Where the broken playbook hurts most, and what’s actually working 💡 The trends ready to reshape how we plan next year If you’re rethinking your 2026 strategy, this hour will be worth it. 📅 When? December 18 Save your spot and see how today’s lessons can transform tomorrow’s marketing: 👇 https://lnkd.in/ehANwz_B #MarketingStrategy #AIMarketing #DigitalMarketing #ContentMarketing #MarketingLeadership …more This is probably the last time you’ll see these three quiet... 30 3 Comments Like Comment Share Kaltura 83,404 followers 4w Edited Report this post With 𝐓𝐢𝐭𝐥𝐞 𝐈𝐈 compliance deadlines approaching, educators need solutions without more stress. ♿✨ Manual processes and disconnected tools are causing institutional roadblocks that slow accessibility progress and strain already-stretched teams. Join Robert Schiller (Director of Ed Tech Sales, Kaltura) and Erik Ducker (Sr. Director of Product Marketing, 3Play Media ) to learn how AI-powered video workflows are helping institutions simplify compliance, boost accessibility, and deliver inclusive learning at scale. You’ll learn how to: 💡 Save manual labor and speed up turnaround with automated captions and audio descriptions 💡 Streamline compliant workflows within your LMS and content systems 💡 Support equity and inclusion with tech that's built to scale with your institution 📆 When? December 17 Sign up to see accessibility in action: 👇 https://lnkd.in/dW2BfKpX #Accessibility #HigherEd #AIinEducation #Kaltura …more Title II deadlines are approaching. Ready to simplify compliance? 10 Like Comment Share Kaltura 83,404 followers 1mo Report this post ↴ Accessibility can’t stay a side project when Title II is around the corner. In this simulive walkthrough, Kaltura and 3Play Media will unpack how to make compliant captions and audio descriptions an automatic part of your content lifecycle. Here’s what we’ll explore: - integrated accessibility functions that run inside everyday workflows - frictionless captioning pipelines that save time and reduce bottlenecks - ways to scale inclusion across campuses without compromising quality Save your spot: https://lnkd.in/d284QVjj #kalturawebinars #accessibility #simulive …more 18 Like Comment Share Join now to see what you are missing Find people you know at Kaltura Browse recommended jobs for you View all updates, news, and articles Join now Similar pages monday.com Software Development Tel Aviv, Israel Vimeo Software Development New York, NY Brightcove Online Audio and Video Media Boston, Massachusetts Gong Software Development San Francisco, California Remepy Biotechnology Research New York, NY Wix Software Development Taboola Software Development New York, NY Wiz Computer and Network Security New York, NY Akamai Technologies Technology, Information and Internet Cambridge, MA Panopto IT Services and IT Consulting Pittsburgh, PA Show more similar pages Show fewer similar pages Browse jobs Kaltura jobs 101 open jobs Project Manager jobs 253,048 open jobs Engineer jobs 555,845 open jobs Manager jobs 1,880,925 open jobs Analyst jobs 694,057 open jobs Account Executive jobs 71,457 open jobs Student jobs 634,404 open jobs Marketing Manager jobs 106,879 open jobs Product Designer jobs 45,389 open jobs Sales Manager jobs 310,050 open jobs Account Manager jobs 121,519 open jobs Customer Success Manager jobs 112,728 open jobs Team Lead jobs 1,056,618 open jobs Scientist jobs 48,969 open jobs Support Engineer jobs 294,729 open jobs Developer jobs 258,935 open jobs Quality Assurance Engineer jobs 31,450 open jobs Human Resources Specialist jobs 34,340 open jobs Intern jobs 71,196 open jobs Associate jobs 1,091,945 open jobs Show more jobs like this Show fewer jobs like this Funding Kaltura 7 total rounds Last Round Series F Sep 8, 2016 External Crunchbase Link for last round of funding US$ 50.0M Investors Goldman Sachs Growth Equity See more info on crunchbase More searches More searches Kaltura jobs Engineer jobs Manager jobs Account Executive jobs Project Manager jobs Account Manager jobs Product Designer jobs Specialist jobs Analyst jobs Developer jobs Business Development Representative jobs Researcher jobs Sales Director jobs Associate jobs Scientist jobs Media Planner jobs Director jobs Consultant jobs Enterprise Account Executive jobs Business Development Specialist jobs Marketing Manager jobs Python Developer jobs iOS Developer jobs Content Specialist jobs Joomla Developer jobs Group Manager jobs Online Marketing Executive jobs Software Engineering Manager jobs Machine Learning Engineer jobs Scrum Master jobs Partner jobs Malware Analyst jobs Channel Partner jobs Ecommerce Developer jobs Advertising Sales Director jobs User Experience Designer jobs Marketer jobs Media Sales Manager jobs Business Application Manager jobs Architect jobs Designer jobs Marketing Specialist jobs Sales Manager jobs Client Manager jobs Product Manager jobs Associate Product Manager jobs Team Lead jobs Quality Assurance Specialist jobs Magento Developer jobs Software Team Lead jobs Software Automation Engineer jobs Office Manager jobs Clinical Research Associate jobs Marketing Analyst jobs Search Engine Optimization Analyst jobs Marketing Data Analyst jobs Digital Marketing Specialist jobs Application Analyst jobs Security Architect jobs Application Engineer jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Kaltura Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#teams-of-developers | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
https://huggingface.co/datasets/ScienceOne-AI/S1-MMAlign | ScienceOne-AI/S1-MMAlign · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: ScienceOne-AI / S1-MMAlign like 70 Tasks: Image-to-Text Visual Question Answering Feature Extraction Modalities: Image Text Formats: webdataset Languages: English Size: 10M - 100M ArXiv: arxiv: 2601.00264 Tags: science multimodal physics biology chemistry engineering + 1 Libraries: Datasets WebDataset Croissant License: cc-by-nc-4.0 Dataset card Data Studio Files Files and versions xet Community 5 Dataset Viewer (First 5GB) Auto-converted to Parquet API Embed Duplicate Data Studio Subset (1) default · ~21.1M rows (showing the first 31k) default (~21.1M rows, showing the first 31k) Split (1) train · ~21.1M rows (showing the first 31k) train (~21.1M rows, showing the first 31k) SQL Console png image width (px) 52 55.2k __key__ string lengths 26 28 __url__ string classes 1 value 0705/0501163.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0501163.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0501163.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0501163.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig010 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig007 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig005 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig008 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig011 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig006 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0307144.tar.gz/fig009 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/9810032.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/9810032.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/9810032.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0309053.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig014 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig010 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig013 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig012 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig007 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig005 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig008 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig011 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig006 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412357.tar.gz/fig009 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig014 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig010 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig013 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig019 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig012 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig017 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig015 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig007 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig016 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig005 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig008 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig018 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig011 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig006 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0304072.tar.gz/fig009 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0510599.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0510599.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0510599.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0510599.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig010 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig012 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig007 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig005 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig008 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig011 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig006 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0007097.tar.gz/fig009 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0403129.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0403129.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0403129.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig007 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig005 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0412585.tar.gz/fig006 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig021 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig014 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig010 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig013 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig019 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig012 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig003 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig017 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig015 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig007 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig016 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig005 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig001 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig020 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig002 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig008 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig018 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig011 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig006 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0704.1453.tar.gz/fig009 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz 0705/0505024.tar.gz/fig004 hf://datasets/ScienceOne-AI/S1-MMAlign@54213db4b5eefffc37982f3a93bac92034db9b70/arxiv/images_2007.tar.gz End of preview. Expand in Data Studio Previous 1 2 3 ... 310 Next Dataset Information How was the data processed? Note on File Structure Citation License and Copyright S1-MMAlign A Large-Scale Multi-Disciplinary Scientific Multimodal Dataset S1-MMAlign is a large-scale, multi-disciplinary multimodal dataset comprising over 15.5 million high-quality image-text pairs derived from 2.5 million open-access scientific papers. Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap between complex scientific imagery and sparse textual descriptions. S1-MMAlign aims to bridge this gap. Unlike simple "image-reading," scientific understanding requires traversing multiple semantic layers involving variables, structures, hypotheses, and inferences. This dataset is built to address this "short board" in current data resources. The dataset captures diverse visual modalities—including experimental setups, heatmaps, and microscopic imagery—spanning major disciplines such as Mathematics, Physics, Chemistry, Biology, Astronomy, Earth Science, Medicine, Engineering, and Computer Science . We anticipate that researchers and enthusiasts will utilize this dataset for training foundational AI for Science models, advancing scientific reasoning, and improving cross-modal understanding in specialized domains. Dataset Information Total Image-Text Pairs: > 15,500,000 Source Papers: ~ 2,500,000 Disciplines Covered: 9 Major STEM Fields Alignment Improvement: +18.21% (CLIP Score vs. Raw Data) License: CC BY-NC 4.0 How was the data processed? To address the pervasive issue of weak alignment in raw scientific captions, we introduced an AI-ready semantic enhancement pipeline. We utilized the Qwen-VL multimodal large model series to recaption images by synthesizing context from paper abstracts and citation contexts. Technical validation demonstrates significant quality improvements: SciBERT-based pseudo-perplexity metrics show reduced semantic ambiguity, while CLIP scores indicate an 18.21% improvement in image-text alignment. Recommendation: Please use the recaption field for model training. image_path : The relative path to the image file. recaption (Recommended): The AI-enhanced caption generated by our pipeline (Qwen-VL). It synthesizes context from the paper abstract and citations to provide a semantically rich description, significantly outperforming the raw caption in alignment and quality. caption : The original, raw caption extracted from the paper figures (often noisy or sparse). metadata : Additional information including source paper arxiv_id and title. Note on File Structure The relative paths of the images provided in the jsonl file must follow the file structure we provide in order to be used correctly. Please ensure you maintain the directory hierarchy after downloading and decompressing the dataset. Do not flatten the folder structure, as the metadata relies on specific relative paths. Citation If you find this dataset useful, please cite our work: @article{s1mmalign2026, title={S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure–Text Understanding}, author={He Wang and Longteng Guo and Pengkang Huo and Xuanxu Lin and Yichen Yuan and Jie Jiang and Jing Liu}, journal={ArXiv preprint}, url={https://arxiv.org/abs/2601.00264}, year={2026} } License and Copyright This dataset is released under the CC BY-NC 4.0 license for research and non-commercial use only. Non-Commercial: Commercial use of the dataset or any images is strictly prohibited. Copyrights: The images contained in this dataset are extracted from publicly accessible scientific publications. All copyrights of the original figures remain with their original authors or publishers. Compliance: Users must ensure their use complies with the copyrights of the original publications. Downloads last month 7,540 Use this dataset Size of the auto-converted Parquet files (First 5GB): 4.77 GB Number of rows (First 5GB): 31,000 Estimated number of rows: 21,083,375 Paper for ScienceOne-AI/S1-MMAlign S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding Paper • 2601.00264 • Published 12 days ago System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://pt.linkedin.com/company/cloudflare | Cloudflare | LinkedIn Pular para conteúdo principal LinkedIn Artigos Pessoas Learning Vagas Jogos Cadastre-se agora Entrar Cloudflare Segurança de redes e computadores San Francisco, California 1.123.490 seguidores Na Cloudflare, temos objetivos ambiciosos: ajudar na construção de uma Internet melhor. Visualizar vagas Seguir Visualizar todos os 6.532 funcionários Denunciar esta empresa Visão geral Vagas Dia a dia Sobre nós Cloudflare, Inc. (NYSE: NET) is the leading connectivity cloud company. It empowers organizations to make their employees, applications and networks faster and more secure everywhere, while reducing complexity and cost. Cloudflare’s connectivity cloud delivers the most full-featured, unified platform of cloud-native products and developer tools, so any organization can gain the control they need to work, develop, and accelerate their business. Powered by one of the world’s largest and most interconnected networks, Cloudflare blocks billions of threats online for its customers every day. It is trusted by millions of organizations – from the largest brands to entrepreneurs and small businesses to nonprofits, humanitarian groups, and governments across the globe. Site https://www.cloudflare.com Link externo para Cloudflare Setor Segurança de redes e computadores Tamanho da empresa 1.001-5.000 funcionários Sede San Francisco, California Tipo Empresa de capital aberto Fundada em 2009 Especializações nginx, lua, go, web performance, web security, dns, network, noc, nocc, ddos, CDN, waf, zero trust security e developer tools Produtos Ver todos Não há mais conteúdo anterior Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Software de gerenciamento de identidade e acesso Cloudflare Access Software de gerenciamento de identidade e acesso Cloudflare CDN, Software de rede de entrega de conteúdo Cloudflare CDN Software de rede de entrega de conteúdo Cloudflare DDoS Protection, Software de proteção contra ataques DDoS Cloudflare DDoS Protection Software de proteção contra ataques DDoS Cloudflare DNS, Software de serviços de DNS gerenciados Cloudflare DNS Software de serviços de DNS gerenciados Cloudflare Load Balancing, Software de balanceamento de carga Cloudflare Load Balancing Software de balanceamento de carga Cloudflare Registrar, Software de serviços de DNS gerenciados Cloudflare Registrar Software de serviços de DNS gerenciados Cloudflare Spectrum, Software de proteção contra ataques DDoS Cloudflare Spectrum Software de proteção contra ataques DDoS Cloudflare SSL / TLS, Software de certificados SSL Cloudflare SSL / TLS Software de certificados SSL Cloudflare Stream, Software de transmissão ao vivo Cloudflare Stream Software de transmissão ao vivo Não há mais próximo conteúdo Produtos Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Software de gerenciamento de identidade e acesso Cloudflare Access Software de gerenciamento de identidade e acesso Cloudflare CDN, Software de rede de entrega de conteúdo Cloudflare CDN Software de rede de entrega de conteúdo Cloudflare DDoS Protection, Software de proteção contra ataques DDoS Cloudflare DDoS Protection Software de proteção contra ataques DDoS Cloudflare DNS, Software de serviços de DNS gerenciados Cloudflare DNS Software de serviços de DNS gerenciados Cloudflare Load Balancing, Software de balanceamento de carga Cloudflare Load Balancing Software de balanceamento de carga Cloudflare Registrar, Software de serviços de DNS gerenciados Cloudflare Registrar Software de serviços de DNS gerenciados Cloudflare Spectrum, Software de proteção contra ataques DDoS Cloudflare Spectrum Software de proteção contra ataques DDoS Cloudflare SSL / TLS, Software de certificados SSL Cloudflare SSL / TLS Software de certificados SSL Cloudflare Stream, Software de transmissão ao vivo Cloudflare Stream Software de transmissão ao vivo Cloudflare WAF, Firewalls de aplicativos web Cloudflare WAF Firewalls de aplicativos web Cloudflare Web Analytics, Software de análise digital Cloudflare Web Analytics Software de análise digital Cloudflare Workers, Software de virtualização de servidor Cloudflare Workers Software de virtualização de servidor Localidades Principal 101 Townsend St San Francisco, California 94107, US Como chegar Westminster Bridge Road 6th Floor, Riverside Building, County Hall London, England SE1 7PB, GB Como chegar 120 Robinson Road Frasers Tower #35-01 Singapore, Singapore 069547, SG Como chegar 405 Comal St Austin, Texas 78702, US Como chegar 10 Almaden Blvd Suite 200 San Jose, California 95113, US Como chegar Rosental 7 Munich, Bavaria 80331, DE Como chegar 301 N Neil St Suite 440 Champaign, Illinois 61820, US Como chegar 26-1 Sakuragaoka-cho Shibuya-ku, Level 15 Cerulean Tower Tokyo, 150-8512, JP Como chegar 16 South Guangshun Street Donghuang Building 17th Floor Beijing, Chaoyang District Beijing 100015, CN Como chegar Rue de la Loi 38 Brussels, Brussels Region 1000, BE Como chegar Praça Marquês de Pombal 14 7th floor Lisbon, 1250-162, PT Como chegar 6, Place de la Madeleine Mailing Address Only Paris, Île-de-France 75008, FR Como chegar 20 Martin Place Level 10 Sydney, NSW 2000, AU Como chegar 1401 K St NW Washington, District of Columbia 20005, US Como chegar Exibir mais localidades Exibir menos localidades Funcionários da Cloudflare Adam Edgmond Mark Nottingham Trevor Laughton Carl Ledbetter Ver todos os funcionários Atualizações Cloudflare 1.123.490 seguidores 8 h Denunciar esta publicação As we kick off the new year, we’re spotlighting Cloudflare leaders across multiple functions who will share their insights around technical trends and emerging threats in 2026. 🎥 Nan Hao Maguire, APAC & Japan Field CTO at Cloudflare, breaks down the urgent shifts in the threat landscape, from smarter AI-driven attacks to the emerging reality of quantum computing. Discover our technical predictions for 2026 in our Post Quantum Computing solution brief: https://cfl.re/3LyW1eC #Cybersecurity #QuantumComputing #AI #FutureofTech #Infrastructure #2026Trends …mais 25 2 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 14 h Denunciar esta publicação The margin is thinner than you think with modernizing applications. 📉 14% are behind schedule. 13% are ahead of schedule. This 1% difference can make or break your ability to innovate with AI. 🤖 Find out how in the 2026 Cloudflare App Innovation Report, dropping this Wednesday. 🚀 #AppInnovationReport #TechnologyInnovation #CyberSecurity 35 4 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 3 d Denunciar esta publicação 🤠 Dallas! The future of connectivity is coming to Frisco. Ready to connect with the leaders driving network modernization right here in Texas? Join us for Cloudflare Immerse Dallas on February 12th! We’re bringing together the region’s top security, IT, and digital leaders for an afternoon of deep dives into the Connectivity Cloud, Zero Trust, and AI application security. It’s more than just sessions—it’s your chance to network with peers and get your toughest questions answered at our "Ask the Cloudflare Experts" bar. 📍 Where: HALL Park Hotel, Frisco, TX 📅 When: Thursday, Feb 12, 2026 | 1:30 PM - 5:00 PM (Happy Hour to follow! 🍹) Spots are limited. Secure your seat today! 👇 https://lnkd.in/dEKuBqve #CloudflareImmerse #DallasTech #NetSec #FriscoTX #Networking #CyberSecurity #ConnectivityCloud 50 4 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 4 d Denunciar esta publicação What's your preferred method for knowledge sharing within a team (e.g., detailed READMEs, synchronous workshops, pairing)? #CloudflareChat 29 8 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 4 d Denunciar esta publicação We are thrilled to announce that Cloudflare has been recognized as the current Company to Beat in the December 2025 Gartner AI Vendor Race for Edge Distribution Platform AI! Discover the key findings of the report from our article 👇 Cloudflare named as the current Company to Beat in a Gartner® report for Edge Distribution Platform AI! Cloudflare no LinkedIn 657 11 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 5 d Editado Denunciar esta publicação Cloudflare is getting ready for ICE 2026 in Barcelona, taking place 19–21 January. We’ll be at Booth 4K30 sharing how Cloudflare for iGaming helps platforms deliver fast, secure, and reliable experiences for players around the world. If you’re attending, stop by to meet the team, explore our iGaming security solutions, and join us for a relaxed Happy Hour at the booth. If you pre-book a meeting with us, you’ll also be entered into a prize draw for a chance to win an exclusive FC Barcelona jersey on the first day of the event! Click here to book your meeting: https://lnkd.in/gSPe58K6 See you there! 33 Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 5 d Denunciar esta publicação Is your organization struggling to manage a sprawling attack surface across hybrid environments? Join Cloudflare and Werner Executive VP & CIO Daragh Mahon to hear directly from one of our customers on their successful real-world Zero Trust deployments. Learn more about priority use cases, common challenges, and architectural strategies. Register today! https://lnkd.in/db4Gb6Rk #ZeroTrust #Cybersecurity #Cloudflare #Webinar 41 2 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 5 d Denunciar esta publicação Defend against rising app-layer DDoS attacks 📱 In his latest article for theNET, Gregory Van den Top explains how DDoS attacks — often powered by AI — are a growing threat to applications. They can slow or completely crash software, bringing critical operations to a halt. The right strategic framework — focused on detecting, mitigating, and adapting — can help stop attacks and improve resilience: https://lnkd.in/dwuSqcm4 60 1 comentário Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 6 d Denunciar esta publicação A BGP route leak in Venezuela recently impacted internet connectivity. Our latest analysis breaks down how this happened and why it highlights the need for better routing security across the global Internet. https://cfl.re/4qEaNQ5 A closer look at a BGP anomaly in Venezuela blog.cloudflare.com 358 4 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 6 d Denunciar esta publicação Cloudflare was proud to protect the Moldovan Central Election Commission during their elections. 🔗 Learn more about it on our blog: https://lnkd.in/gQ8P2NmB Anatolie Golovco 1 sem CloudFlare mentioned Moldova in their 2025 Annual Impact Report. As a personal tip to web studios that care about protecting their customers against DDoS attacks: take a look at CloudFlare Pages, CloudFlare R2, and Hugo CMS as alternatives to traditional hosting setups and content management systems. https://lnkd.in/dxgycsYm #CloudFlare 41 2 comentários Gostei Comentar Compartilhar Cadastre-se agora para ver o que você está perdendo Encontre pessoas conhecidas na Cloudflare Veja vagas recomendadas para você Visualize todas as atualizações, notícias e artigos Cadastre-se agora Páginas afiliadas Cloudflare for Public Sector Segurança de redes e computadores San Francisco, California Cloudflare Partner Network Segurança de redes e computadores Páginas semelhantes Akamai Technologies Tecnologia, Informação e Internet Cambridge, MA CrowdStrike Segurança de redes e computadores Palo Alto Networks Segurança de redes e computadores SANTA CLARA, California Atlassian Desenvolvimento de software Sydney, NSW Google Desenvolvimento de software Mountain View, CA Zscaler Segurança de redes e computadores San Jose, California Snowflake Desenvolvimento de software Microsoft Desenvolvimento de software Redmond, Washington Cisco Desenvolvimento de software San Jose, CA Databricks Desenvolvimento de software San Francisco, CA Exibir mais páginas semelhantes Exibir menos páginas semelhantes Visualizar vagas Vagas de Engenheiro 422 vagas Vagas de Executivo de contas 51 vagas Vagas de Analista 269 vagas Vagas de Diretor 280 vagas Vagas de Desenvolvedor 372 vagas Vagas de Gerente de vendas 116 vagas Vagas de Gerente de Marketing 141 vagas Vagas de Diretor de recursos humanos 27 vagas Vagas de Gerente de engenharia 139 vagas Vagas de Analista de dados 5.002 vagas Vagas de Desenvolvedor Python 972 vagas Vagas de Gerente de TI 57 vagas Vagas de Recrutador 27 vagas Vagas de Recursos humanos 913 vagas Vagas de Diretor de RH 43 vagas Vagas de CEO 399 vagas Vagas de Arquiteto 67 vagas Vagas de Engenheiro de dados 37 vagas Vagas de Redator 48 vagas Vagas de Comprador 64 vagas Exibir mais vagas como essa Exibir menos vagas como essa Mais pesquisas Mais pesquisas Vagas de Engenheiro Vagas de Diretor Vagas de Executivo de contas Vagas de Analista Vagas de Desenvolvedor Vagas de Gerente de vendas Vagas de Gerente de engenharia Vagas de Recrutador Vagas de Gerente de Marketing Vagas de Analista de dados Vagas de Desenvolvedor Python Vagas de Recursos humanos Vagas de Engenheiro de dados Vagas de CEO Vagas de Gerente de TI Vagas de Arquiteto Vagas de CTO Vagas de Marketing Vagas de Diretor de recursos humanos Vagas de Redator Vagas de Diretor de RH Vagas de Desenvolvedor Javascript Vagas de Analista de sistema Vagas de Gerente de eventos Vagas de Analista de riscos Vagas de Financeiro Vagas de Scrum master Vagas de Desenvolvedor .Net Vagas de Gerente comercial Vagas de Engenheiro de software Vagas de Arquiteto de software Vagas de Coordenador de marketing Vagas de Analista de marketing Vagas de Auditor Vagas de Engenheiro de qualidade Vagas de Desenvolvedor de aplicativos Vagas de Analista de investimento Vagas de Diretor de projetos Vagas de Analista financeiro Vagas de Diretor financeiro Vagas de Jornalista Vagas de Engenheiro industrial Vagas de Engenheiro de projetos Vagas de Assistente de marketing Vagas de Comprador Vagas de Assistente de pesquisa Vagas de Analista de vendas Vagas de Testador de software Vagas de Economista Vagas de Diretor de vendas Vagas de Diretor comercial Vagas de Analista de RH Vagas de Historiador Vagas de Auditor interno Vagas de Direito Vagas de Auxiliar financeiro Vagas de Docente Vagas de Copywriter Vagas de Advogado Vagas de Optometrista LinkedIn © 2026 Sobre Acessibilidade Contrato do Usuário Política de Privacidade do LinkedIn Política de Cookies Política de Direitos Autorais Política da Marca Controles de visitantes Diretrizes da Comunidade العربية (Árabe) বাংলা (Bengali) Čeština (Tcheco) Dansk (Dinamarquês) Deutsch (Alemão) Ελληνικά (Grego) English (Inglês) Español (Espanhol) فارسی (Persa) Suomi (Finlandês) Français (Francês) हिंदी (Hindi) Magyar (Húngaro) Bahasa Indonésia (Indonésio) Italiano (Italiano) עברית (Hebraico) 日本語 (Japonês) 한국어 (Coreano) मराठी (Marati) Bahasa Malaysia (Malaio) Nederlands (Holandês) Norsk (Norueguês) ਪੰਜਾਬੀ (Punjabi) Polski (Polonês) Português (Português) Română (Romeno) Русский (Russo) Svenska (Sueco) తెలుగు (Telugu) ภาษาไทย (Tailandês) Tagalog (Tagalog) Türkçe (Turco) Українська (Ucraniano) Tiếng Việt (Vietnamita) 简体中文 (Chinês (Simplificado)) 正體中文 (Chinês (Tradicional)) Idioma Aceite e cadastre-se no LinkedIn Ao clicar em Continuar para se cadastrar ou entrar, você aceita o Contrato do Usuário , a Política de Privacidade e a Política de Cookies do LinkedIn. Entre para ver quem você já conhece na empresa Cloudflare Entrar Olá novamente E-mail ou telefone Senha Exibir Esqueceu a senha? Entrar ou Ao clicar em Continuar para se cadastrar ou entrar, você aceita o Contrato do Usuário , a Política de Privacidade e a Política de Cookies do LinkedIn. Nunca usou o LinkedIn? Cadastre-se agora ou Nunca usou o LinkedIn? Cadastre-se agora Ao clicar em Continuar para se cadastrar ou entrar, você aceita o Contrato do Usuário , a Política de Privacidade e a Política de Cookies do LinkedIn. | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/t-systems-business-cockpit/ | Business Cockpit | LinkedIn Skip to main content LinkedIn T-Systems International in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Business Cockpit Business Process Management Software by T-Systems International See who's skilled in this Add as skill Learn more Report this product About Das Business Cockpit ist ein Service, der es ermöglicht, Business Objekte (z.B. Fahrzeuge, Lieferungen) und deren Prozessdurchläufe in Echtzeit graphisch darzustellen und analytisch auszuwerten. Durch ein systemübergreifendes Tracking erkennen Sie schnell Anomalien, können Entscheidungen auf Basis aktueller Fakten treffen und sofort eingreifen. Verringern Sie Prozesskosten und beschleunigen Sie Ihre Abläufe durch gezielte Ursachenanalyse auch von historischen Daten. This product is intended for Manager Process Manager Automotive Manager Business Analyst Senior Business Analyst Project Manager Automotive Consultant Logistics Specialist Media Products media viewer No more previous content Business Cockpit Erklärvideo Das Business Cockpit ist ein Service, der es ermöglicht, Business Objekte (z.B. Fahrzeuge, Lieferungen) und deren Prozessdurchläufe in Echtzeit graphisch darzustellen und analytisch auszuwerten. Durch ein systemübergreifendes Tracking erkennen Sie schnell Anomalien, können Entscheidungen auf Basis aktueller Fakten treffen und sofort eingreifen. Verringern Sie Prozesskosten und beschleunigen Sie Ihre Abläufe durch gezielte Ursachenanalyse auch von historischen Daten. Business Cockpit Onepager Das Business Cockpit ist ein Service, der es ermöglicht, Business Objekte (z.B. Fahrzeuge, Lieferungen) und deren Prozessdurchläufe in Echtzeit graphisch darzustellen und analytisch auszuwerten. Durch ein systemübergreifendes Tracking erkennen Sie schnell Anomalien, können Entscheidungen auf Basis aktueller Fakten treffen und sofort eingreifen. Verringern Sie Prozesskosten und beschleunigen Sie Ihre Abläufe durch gezielte Ursachenanalyse auch von historischen Daten. Business Cockpit Interview Das Business Cockpit ist ein Service, der es ermöglicht, Business Objekte (z.B. Fahrzeuge, Lieferungen) und deren Prozessdurchläufe in Echtzeit graphisch darzustellen und analytisch auszuwerten. Durch ein systemübergreifendes Tracking erkennen Sie schnell Anomalien, können Entscheidungen auf Basis aktueller Fakten treffen und sofort eingreifen. Verringern Sie Prozesskosten und beschleunigen Sie Ihre Abläufe durch gezielte Ursachenanalyse auch von historischen Daten. No more next content Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less T-Systems International products CARbon Footprint Fleet Optimizer CARbon Footprint Fleet Optimizer Sustainability Software Content as a Service (CaaS) Content as a Service (CaaS) Enterprise Content Management (ECM) Software DocuSign DocuSign E-Signature Software ImageMaster ImageMaster Enterprise Content Management (ECM) Software Limago Limago Translation Management Software MatchMaker MatchMaker Automotive Marketing Software Open Telekom Cloud Open Telekom Cloud Infrastructure as a Service (IaaS) Recycling App Recycling App Sustainability Software TypeMaster TypeMaster Enterprise Content Management (ECM) Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://au.linkedin.com/company/macropod-global?trk=organization_guest_main-feed-card-text | Macropod | LinkedIn Skip to main content LinkedIn Articles People Learning Jobs Games Sign in Join for free Macropod Financial Services Macropod is a issuer of a regulated AUD pegged stablecoin. Follow View all 12 employees Report this company About us Macropod is an issuer of an AUD pegged stablecoin. Through the thoughtful application of emerging technology, Macropod empowers businesses and asset exchanges to facilitate fast and cost-effective transactions securely. With over 100 years of combined global experience, Macropod's team has a wealth of financial markets, governance, and technology knowledge to support their customers’ and partners’ successful transition to digital assets. Website www.macropod.com External link for Macropod Industry Financial Services Company size 2-10 employees Headquarters Sydney Type Privately Held Founded 2024 Specialties Blockchain, Stablecoins, Payments, and Cryptocurrency Locations Primary Sydney, AU Get directions Employees at Macropod Delia Burrage Edward Carroll Femi Eboreime Kate Judd See all employees Updates Macropod 831 followers 9h Report this post Your 2026 𝐧𝐨 𝐫𝐨𝐨-𝐠𝐫𝐞𝐭𝐬 listen, Macropod and JellyC - Digital Asset Management 's Unblocking the Chain podcast. Catch every episode here 👉 https://lnkd.in/gGnyEDbG Thanks for the shoutout, Digital Economy Council of Australia (DECA) ! 🦘 Digital Economy Council of Australia (DECA) 16,292 followers 10h Four podcasts worth your ears as the year kicks off. If January is about resetting habits, your podcast queue might need a little refresh too. Whether you are commuting, or avoiding another screen, these shows cut through the noise and get to what actually matters in digital assets, markets and policy. Unblocking the Chain Produced by JellyC - Digital Asset Management and Macropod this series explores the intersection of traditional finance and digital assets, investment strategies, macro trends and central bank policy. Hosted by Michael "Critta" Prendiville and Drew Bradford. ~ Show Link: https://lnkd.in/gZMHEXyq TRM Talks Every other week, Ari Redbord Global Head of Policy at TRM Labs speaks with policymakers, investigators and industry leaders on digital asset policy, regulation and enforcement. ~ Show Link: https://lnkd.in/gZgXzpHr Independent Reserve Podcast Clear, practical discussions covering digital assets, market developments and industry insights, designed to be accessible for diverse audiences. Hosted by Lee Eaton . ~ Show Link: https://lnkd.in/gqAWDdxR Crypto Curious Hosted by Tracey Plowman , Blake Cassidy and Craig Jackson, this weekly podcast breaks down digital assets in a straightforward way, with a focus on trends shaping the market. ~ Show link: https://lnkd.in/gSFPMRsq Head to the DECA resources page where we amplify the podcasts, education, research, tools and insights produced by our members across digital assets, policy, markets and infrastructure. https://lnkd.in/gTQ6eN8j We're here to support industry and our members. Learn more about membership and how to get involved: 🔗 https://lnkd.in/gjmpi4kA 3 Like Comment Share Macropod 831 followers 4d Edited Report this post AUDM has taken its next leap and landed safely at Zodia Custody , our first custodian partner. 👇 🦘 Zodia Custody 23,287 followers 5d We now support Macropod’s AUDM stablecoin 🦘 Zodia Custody is the first custodian to support AUDM, the Australian dollar-backed stablecoin issued by Macropod , Australia’s first licensed stablecoin issuer. Drew Bradford , CEO of Macropod said: “We’re pleased to see AUDM supported by Zodia Custody, following the successful development of use cases through the Reserve Bank of Australia’s Project Acacia. This integration reinforces the importance of institutional-grade custody especially as stablecoins move into mainstream financial infrastructure.” With AUDM now live on Zodia Custody, institutions can hold this new settlement asset within secure custody built for scale, governance and institutional trust. Another hop forward for Australia’s digital asset ecosystem 🇦🇺 #ZodiaCustody #stablecoins #Macropod #AUDM 12 1 Comment Like Comment Share Macropod 831 followers 5d Report this post 2025–26: 𝐂𝐫𝐲𝐩𝐭𝐨 𝐠𝐞𝐭𝐬 𝐢𝐭𝐬 𝐚𝐜𝐭 𝐭𝐨𝐠𝐞𝐭𝐡𝐞𝐫 Last year, 𝐜𝐫𝐲𝐩𝐭𝐨 𝐬𝐭𝐨𝐩𝐩𝐞𝐝 𝐩𝐥𝐚𝐲𝐢𝐧𝐠 𝐚𝐫𝐨𝐮𝐧𝐝 𝐚𝐧𝐝 𝐛𝐞𝐜𝐚𝐦𝐞 𝐬𝐞𝐫𝐢𝐨𝐮𝐬. In the latest episode of Unblocking the Chain, Drew Bradford and Michael "Critta" Prendiville unpack that inflection point: how crypto went from “interesting experiment” to essential infrastructure. The highlights? Regulatory clarity that actually landed. Institutions that stopped dipping toes and dove in. ETFs that grew faster than Jack’s beanstalk. Stablecoins and tokenisation hitting their stride. 🦘 Our 2026 outlook focuses on the 𝐮𝐧𝐠𝐥𝐚𝐦𝐨𝐮𝐫𝐨𝐮𝐬 𝐛𝐮𝐭 𝐜𝐫𝐢𝐭𝐢𝐜𝐚𝐥 𝐰𝐨𝐫𝐤 that will define the next phase: payments infrastructure, FX rails, atomic settlement, and how AI agents will interact with on-chain systems. If you’re building, investing, or just trying to figure out where this space is actually headed, this one’s for you. 🫡 🎧 Apple: https://lnkd.in/g6nScPaB 🎧 Spotify: https://lnkd.in/gJXBZPHD 🎧 Youtube: https://lnkd.in/g-95xjQP #MadeInAustralia #AussieFinTech #DigitalAssets #Blockchain #Stablecoins #Tokenisation #CryptoInfrastructure …more From 2025 to 2026: Crypto’s Defining Shift https://www.youtube.com/ 17 Like Comment Share Macropod 831 followers 1w Edited Report this post 𝐁𝐢𝐠 (𝐑𝐞𝐝) 𝐧𝐞𝐰𝐬 𝐭𝐨 𝐤𝐢𝐜𝐤 𝐨𝐟𝐟 𝐭𝐡𝐞 𝐲𝐞𝐚𝐫! 🦘 Clients of the 𝐌𝐚𝐜𝐫𝐨𝐩𝐨𝐝 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦 can now 𝐦𝐢𝐧𝐭 𝐚𝐧𝐝 𝐫𝐞𝐝𝐞𝐞𝐦 𝐀𝐔𝐃𝐌 directly via macropod.com , making it easier than ever to access compliant, on-chain Australian dollar settlement. Read more: https://lnkd.in/gEpc6HBh 𝐇𝐨𝐩 𝐭𝐨 𝐢𝐭! 🦘 Drew Bradford Delia Burrage Robert Waugh #AUDM #Macropod #Stablecoin #OnChainSettlement #RegulatedCrypto Australia's First Regulated Stablecoin - Now Available Online macropod.com 46 4 Comments Like Comment Share Macropod 831 followers 2w Report this post 𝟮𝟬𝟮𝟱: 𝗕𝗼𝘂𝗻𝗰𝗲 𝗯𝘆 𝗕𝗼𝘂𝗻𝗰𝗲 🦘 Jan: Three founders - Drew Bradford , Delia Burrage & Robert Waugh . By mid-year, a full team building best-in-class infrastructure and governance. 🦘 July: Lead participant in Reserve Bank of Australia & Digital Finance CRC 's #ProjectAcacia - running three pilots in tokenised markets. 🦘 July: ASIC grants Australia's first AFSL expressly for issuing a #stablecoin . 🦘 Sept: Class Order Relief for downstream AUDM trading - brokers, exchanges & market makers can trade without an AFSL. Industry-wide relief follows in Dec. 🦘 Oct: Partnership with MHC Digital Group . 🦘 Oct: AUDM launches on Ethereum & goes live in DeFi: AUDM-USDT, AUDM-USDC & AUDM-ETH pools on Uniswap v3. 🦘 Oct: CEO Drew Bradford ranked 7th in Blockchain APAC 's Digital Asset Impact Top 50 (only politicians and agency heads ranked higher). 🦘 Nov: Digital Economy Council of Australia (DECA) Blockies nominations: Macropod for Financial Services Innovator, Delia for Diversity & Inclusion Leader, Drew for Blockchain Leader of the Year. Drew wins! 🦘 Nov: AUDM available via Zodia Custody . 🦘 Early Dec: AUDM lists on Independent Reserve . 🦘 Mid Dec: Australia's first tokenised corporate bond settles using AUDM on Redbelly Network . 🦘 Late Dec: JellyC - Digital Asset Management acquires equity in Crystal aOS using AUDM - regulated on-chain settlement supporting real corporate activity. 🦘 Late Dec: AUDM goes live natively on Redbelly Network - extending regulated AUD rails to a high-throughput, Australian-built L1. 🦘 24 Dec: 2.62M AUDM in circulation - growing adoption across exchanges, DeFi & on-chain use cases. 𝗧𝗵𝗮𝗻𝗸 𝘆𝗼𝘂 𝘁𝗼 𝗲𝘃𝗲𝗿𝘆𝗼𝗻𝗲 𝘄𝗵𝗼 𝗽𝗹𝗮𝘆𝗲𝗱 𝗮 𝗽𝗮𝗿𝘁 𝗶𝗻 𝘂𝘀 𝗹𝗮𝗻𝗱𝗶𝗻𝗴 𝗼𝗻 𝗼𝘂𝗿 𝗳𝗲𝗲𝘁. 𝗡𝗼𝘄 𝗶𝘁’𝘀 𝘁𝗶𝗺𝗲 𝘁𝗼 𝗿𝗲𝗮𝗹𝗹𝘆 𝘀𝘁𝗿𝗲𝘁𝗰𝗵 𝘁𝗵𝗲 𝗹𝗲𝗴𝘀. 🦘 𝗛𝗮𝗽𝗽𝘆 𝟮𝟬𝟮𝟲! 🎇 79 4 Comments Like Comment Share Macropod 831 followers 2w Report this post While everything else slows down AUDM keeps moving. 🦘 #Stablecoin #Settlement #LedgersAndLeftovers 29 3 Comments Like Comment Share Macropod 831 followers 3w Report this post 🗞️𝐀𝐔𝐃𝐌 𝐣𝐮𝐬𝐭 𝐡𝐨𝐩𝐩𝐞𝐝 𝐨𝐧𝐭𝐨 𝐑𝐞𝐝𝐛𝐞𝐥𝐥𝐲 𝐍𝐞𝐭𝐰𝐨𝐫𝐤 - 𝐭𝐡𝐞 𝐟𝐢𝐫𝐬𝐭 𝐬𝐭𝐚𝐛𝐥𝐞𝐜𝐨𝐢𝐧 𝐢𝐬𝐬𝐮𝐞𝐝 𝐧𝐚𝐭𝐢𝐯𝐞𝐥𝐲 𝐨𝐧 𝐭𝐡𝐞 𝐩𝐥𝐚𝐭𝐟𝐨𝐫𝐦🗞️ This is how Australia builds the future of finance. ✅ Regulatory trust: Fully AFSL-compliant for institutional confidence ✅ Enterprise-grade tech: Built for real-world business at scale ✅ Speed & security: Powered by one of the world's fastest and most secure blockchains, Redbelly Network 𝐑𝐎𝐎𝐥𝐲 𝐩𝐫𝐨𝐮𝐝 𝐦𝐨𝐦𝐞𝐧𝐭! 🦘 Delia Burrage Drew Bradford Robert Waugh #AUDM #Blockchain #DigitalFinance #AustralianFintech #Stablecoins 48 4 Comments Like Comment Share Macropod 831 followers 3w Report this post Stablecoins are emerging as the connective tissue of tokenised markets, delivering instant, atomic settlement while serving as trusted treasury and payments infrastructure. That’s the view of Edward Carroll , Head of Global Markets & Corporate Finance at MHC Digital Group , who identifies #stablecoins as a key growth driver for 2026. He highlights their real-world use across payments, foreign exchange, and tokenised products - including bonds, securities, and ETFs - as essential infrastructure for the next phase of financial markets. MHC Digital Group is a founding partner and joint-venture operator of Macropod . 🦘 Read the full article 👇 #AUDM MHC Digital Group 1,251 followers 3w As we wind down for the holiday season, we’re already looking ahead to what comes next for digital assets. In new commentary, MHC Digital Group outlines why 2026 is expected to mark a pivotal year for institutional adoption, tokenisation, and the mainstreaming of stablecoins. As Edward Carroll notes: “Digital assets are no longer a fringe concept - they are becoming embedded in the fabric of global finance.” With clearer regulation, accelerating institutional flows, and real-world use cases across payments and tokenised markets, the next phase of crypto will be defined less by speculation and more by infrastructure, scale, and utility. Read the full article here: 🔗 https://lnkd.in/gfekWBpn #DigitalAssets #InstitutionalCrypto #Stablecoins #Tokenisation #Bitcoin #FutureOfFinance Crypto poised for long-term growth: MHC Digital - Investor Daily investordaily.com.au 10 Like Comment Share Macropod 831 followers 3w Report this post JellyC - Digital Asset Management ’s first corporate transaction with AUDM is in the pouch, with an investment in Crystal aOS . More of this to come as compliant stablecoin rails enable speed, certainty, and transparency. 👌 🦘 Delia Burrage Drew Bradford Robert Waugh Michael "Critta" Prendiville JellyC - Digital Asset Management 2,649 followers 3w Pleased to share that JellyC has completed its first transaction using Australia’s first regulated AUD stablecoin, AUDM ( Macropod ) — acquiring an interest in Crystal aOS . This marks an important milestone for us, not just in terms of digital asset infrastructure, but in demonstrating how regulated on-chain settlement can be used for real-world corporate transactions, not just trading or payments. Crystal aOS is building AI-powered compliance infrastructure for businesses and funds. We’re excited to support innovation at the intersection of responsible AI, law and compliant digital finance. As regulated stablecoins and tokenised cash rails mature in Australia, we expect to see far more activity like this — faster settlement, reduced friction, and clearer auditability, all within a compliant framework. Michael "Critta" Prendiville Joni Pirovich Drew Bradford Nicholas Mace Laetitia Lynch Jonathan Caldwell Matt Blackwell Tonya Prendiville 20 1 Comment Like Comment Share Macropod 831 followers 3w Edited Report this post 🇦🇺 𝐀𝐮𝐬𝐭𝐫𝐚𝐥𝐢𝐚'𝐬 𝐟𝐢𝐫𝐬𝐭 𝐭𝐨𝐤𝐞𝐧𝐢𝐬𝐞𝐝 𝐜𝐨𝐫𝐩𝐨𝐫𝐚𝐭𝐞 𝐛𝐨𝐧𝐝: 𝐚 𝐡𝐨𝐩, 𝐬𝐤𝐢𝐩, 𝐚𝐧𝐝 𝐚 𝐬𝐞𝐭𝐭𝐥𝐞𝐦𝐞𝐧𝐭 𝐢𝐧 𝐟𝐨𝐮𝐫 𝐦𝐢𝐧𝐮𝐭𝐞𝐬 🦘 𝐓𝐨𝐝𝐚𝐲 𝐦𝐚𝐫𝐤𝐬 𝐭𝐡𝐞 𝐟𝐢𝐫𝐬𝐭-𝐞𝐯𝐞𝐫 𝐭𝐨𝐤𝐞𝐧𝐢𝐬𝐞𝐝 𝐜𝐨𝐫𝐩𝐨𝐫𝐚𝐭𝐞 𝐛𝐨𝐧𝐝 𝐢𝐬𝐬𝐮𝐞𝐝 𝐢𝐧 𝐀𝐮𝐬𝐭𝐫𝐚𝐥𝐢𝐚, and we’re proud that Macropod led the use case. As part of Project Acacia, the bond: Was issued by Imperium Markets on its ASIC -licensed marketplace Settled on Redbelly Network Was paid for and settled using Macropod ’s AUDM stablecoin Was purchased by Barrenjoey Markets Pty Ltd Was secondarily traded to JellyC - Digital Asset Management 𝐂𝐨𝐦𝐩𝐥𝐞𝐭𝐞𝐝 𝐞𝐧𝐝-𝐭𝐨-𝐞𝐧𝐝 𝐢𝐧 𝐟𝐨𝐮𝐫 𝐦𝐢𝐧𝐮𝐭𝐞𝐬, 𝐧𝐨𝐭 𝐟𝐨𝐮𝐫 𝐝𝐚𝐲𝐬. Today’s milestone proved that AUDM can power regulated wholesale markets, boost liquidity, and strengthen Australia’s corporate bond market 24/7. Our namesake may prefer dawn and dusk, but AUDM never takes a break. Credit to Imperium Markets , Barrenjoey Markets Pty Ltd, JellyC - Digital Asset Management , Redbelly Network , and the teams behind Project Acacia, led by the Reserve Bank of Australia and the Digital Finance CRC , for helping Australia leap into the future. Read the full media release below 👇 Drew Bradford Delia Burrage Robert Waugh Michael "Critta" Prendiville Imperium Markets 876 followers 3w Edited Imperium has issued the first tokenised corporate bond in Australia. The bond named CLIFFO Series 1, an acronym for Corporate Loan Investment For Future Obligations was issued in Macropod 's use case in Project Acacia. The transaction was done in addition to Imperium's own successful use cases in Project Acacia, which we will release details of in the coming weeks. Congratulations to Macropod and Redbelly Network for the successful execution using your technology. And a big thanks to Barrenjoey and JellyC - Digital Asset Management for collaborating on the use case to get the transactions done. What the transaction demonstrates is that tokenisation will create a marketplace that provides access for all, it will remove significant risks and deliver enormous efficiencies. All it takes is some courage and a willingness to collaborate. We want to give our good mate Sam Clifford , Head of Credit Sales at CBA, a shout out. He's faced some challenges of his own this year and done it with a lot of courage, and he's reminded us all that you are nothing without your people...and it don't mean much without your mates! The future is bright Cliffo...this ones for you! Drew Bradford Robert Waugh Delia Burrage John Pearce Olivia Attrill Tim Bass Jala Burns Nathan Lusted Rod Lewis Tom Rowe Michael Chandra Melissa V. Sylvia Qiu Adroaldo de 🦾 Andrade Júlio S. Raphael Lima Victor Luna Wellington Grisa Rod Lane Michael "Critta" Prendiville Jack Collopy Vicki Samartgis Jason Rich Digital Finance CRC Tony Bassaly 30 2 Comments Like Comment Share Join now to see what you are missing Find people you know at Macropod Browse recommended jobs for you View all updates, news, and articles Join now Similar pages JellyC - Digital Asset Management Investment Management MHC Digital Group Investment Management Moore Park, New South Wales CloudTech Group Financial Services South Melbourne, Victoria Redbelly Network Software Development Sydney, New South Wales AUDD - Australian Digital Dollar Technology, Information and Internet Melbourne, Victoria Digital Economy Council of Australia (DECA) Industry Associations Independent Reserve Financial Services Sydney, NSW Zerocap Financial Services Melbourne, Victoria Fireblocks Software Development New York, NY Australian Bond Exchange Financial Services Sydney, New South Wales Show more similar pages Show fewer similar pages More searches More searches Analyst jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Macropod Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://confluence.atlassian.com/spaces/BAMBOO/pages/289276551/Bamboo+documentation | Bamboo documentation | Bamboo Data Center 12.1 | Atlassian Documentation Products Bamboo Support Documentation Knowledge base Resources Search Log in View account View requests Log out ... Knowledge base Products Jira Software Project and issue tracking Jira Service Management Service management and customer support Jira Work Management Manage any business project Confluence Document collaboration Bitbucket Git code management See all Resources Documentation Usage and admin help Community Answers, support, and inspiration Suggestions and bugs Feature suggestions and bug reports Marketplace Product apps Billing and licensing Frequently asked questions Log out Log in to account Contact support Training & Certification Cloud Migration Center GDPR guides Enterprise services Atlassian partners Developers User groups Automation for Jira Atlassian.com Page View in Confluence Edit Page Viewport Manage Viewport Confluence Dashboard Space Directory People Directory Bamboo latest Documentation Unable to load Atlassian Support Bamboo 12.1 Documentation Data Center 12.1 Versions 12.1 12.0 11.0 10.2 10.1 10.0 9.6 9.5 9.4 See all Bamboo documentation Bamboo is a continuous integration and delivery tool that ties automated builds, tests, and releases into a single workflow . Get started New to using Bamboo? Get started with some introductory information. Let's start What’s new Read all about the latest changes in Bamboo. Have a look Last modified on Dec 17, 2025 Installing and upgrading See here if you're a new user or you want to move to a newer version. View topics Using Bamboo Learn about the essentials of using Bamboo. View topics Bamboo Best Practice Find out more tips and tricks of using Bamboo. View topics Administering Bamboo Learn more about managing the Bamboo server. View topics Bamboo Specs Learn more about this feature that lets you store build plans configuration as code. View topics Bamboo FAQ Browse through questions frequently asked about Bamboo. View topics Exporting existing plan configuration to Bamboo YAML Specs View topics Bamboo Data Center View topics Powered by Confluence and Scroll Viewport . Atlassian Notice at Collection Privacy Policy Terms of Use Security © Atlassian | 2026-01-13T09:29:16 |
https://confluence.atlassian.com/spaces/BAMBOO1200/pages/1680480250/Bamboo+documentation | Bamboo documentation | Bamboo Data Center 12.0 | Atlassian Documentation Products Bamboo Support Documentation Knowledge base Resources Search Log in View account View requests Log out ... Knowledge base Products Jira Software Project and issue tracking Jira Service Management Service management and customer support Jira Work Management Manage any business project Confluence Document collaboration Bitbucket Git code management See all Resources Documentation Usage and admin help Community Answers, support, and inspiration Suggestions and bugs Feature suggestions and bug reports Marketplace Product apps Billing and licensing Frequently asked questions Log out Log in to account Contact support Training & Certification Cloud Migration Center GDPR guides Enterprise services Atlassian partners Developers User groups Automation for Jira Atlassian.com Page View in Confluence Edit Page Viewport Manage Viewport Confluence Dashboard Space Directory People Directory Bamboo Data Center 12.0 Documentation Unable to load Atlassian Support Bamboo 12.0 Documentation Data Center 12.0 Versions 12.1 12.0 11.0 10.2 10.1 10.0 9.6 9.5 9.4 See all Bamboo documentation Bamboo is a continuous integration and delivery tool that ties automated builds, tests, and releases into a single workflow . Get started New to using Bamboo? Get started with some introductory information. Let's start What’s new Read all about the latest changes in Bamboo. Have a look Last modified on Nov 20, 2025 Installing and upgrading See here if you're a new user or you want to move to a newer version. View topics Using Bamboo Learn about the essentials of using Bamboo. View topics Bamboo Best Practice Find out more tips and tricks of using Bamboo. View topics Administering Bamboo Learn more about managing the Bamboo server. View topics Bamboo Specs Learn more about this feature that lets you store build plans configuration as code. View topics Bamboo FAQ Browse through questions frequently asked about Bamboo. View topics Exporting existing plan configuration to Bamboo YAML Specs View topics Bamboo Data Center View topics Powered by Confluence and Scroll Viewport . Atlassian Notice at Collection Privacy Policy Terms of Use Security © Atlassian | 2026-01-13T09:29:16 |
https://docs.softwareheritage.org/search.html | Search - Software Heritage documentation Skip to main content Back to top Ctrl + K Development API reference Usage Resources Infrastructure More About GitLab PyPI System Status Software Heritage Homepage Development API reference Usage Resources Infrastructure About GitLab PyPI System Status Software Heritage Homepage Search Error Please activate JavaScript to enable the search functionality. Ctrl + K so the DOM is not blocked --> © Copyright 2015-2025 The Software Heritage developers. Created using Sphinx 7.4.7. Built with the PyData Sphinx Theme 0.16.1. | 2026-01-13T09:29:16 |
https://confluence.atlassian.com/spaces/BAMBOO1100/pages/1556383912/Bamboo+documentation | Bamboo documentation | Bamboo Data Center 11.0 | Atlassian Documentation Products Bamboo Support Documentation Knowledge base Resources Search Log in View account View requests Log out ... Knowledge base Products Jira Software Project and issue tracking Jira Service Management Service management and customer support Jira Work Management Manage any business project Confluence Document collaboration Bitbucket Git code management See all Resources Documentation Usage and admin help Community Answers, support, and inspiration Suggestions and bugs Feature suggestions and bug reports Marketplace Product apps Billing and licensing Frequently asked questions Log out Log in to account Contact support Training & Certification Cloud Migration Center GDPR guides Enterprise services Atlassian partners Developers User groups Automation for Jira Atlassian.com Page View in Confluence Edit Page Viewport Manage Viewport Confluence Dashboard Space Directory People Directory Bamboo Data Center 11.0 Documentation Unable to load Atlassian Support Bamboo 11.0 Documentation Data Center 11.0 Versions 12.1 12.0 11.0 10.2 10.1 10.0 9.6 9.5 9.4 See all Bamboo documentation Bamboo is a continuous integration and delivery tool that ties automated builds, tests, and releases into a single workflow . Get started New to using Bamboo? Get started with some introductory information. Let's start What’s new Read all about the latest changes in Bamboo. Have a look Last modified on Apr 30, 2025 Installing and upgrading See here if you're a new user or you want to move to a newer version. View topics Using Bamboo Learn about the essentials of using Bamboo. View topics Bamboo Best Practice Find out more tips and tricks of using Bamboo. View topics Administering Bamboo Learn more about managing the Bamboo server. View topics Bamboo Specs Learn more about this feature that lets you store build plans configuration as code. View topics Bamboo FAQ Browse through questions frequently asked about Bamboo. View topics Exporting existing plan configuration to Bamboo YAML Specs View topics Bamboo Data Center View topics Powered by Confluence and Scroll Viewport . Atlassian Notice at Collection Privacy Policy Terms of Use Security © Atlassian | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=e0U07W0AAAAJ&hl=ko&oe=ASCII | Qinming He - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 4409 2399 h-index 30 20 i10-index 87 37 0 760 380 190 570 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 17 39 36 55 65 74 73 89 130 174 292 238 169 95 105 145 133 177 292 472 674 757 24 공개 액세스 모두 보기 모두 보기 자료 28개 자료 16개 공개 비공개 재정 지원 요구사항 기준 팔로우 Qinming He Zhejiang University , Professor zju.edu.cn의 이메일 확인됨 Blockchain Data mining Machine learning 학술자료 인용 공개 액세스 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Smart contract vulnerability detection using graph neural networks Y Zhuang, Z Liu, P Qian, Q Liu, X Wang, Q He Proceedings of the twenty-ninth international conference on international�… , 2021 498 2021 计算机基础教学的核心任务是计算思维能力的培养——《 九校联盟 (C9) 计算机基础教学发展战略联合声明》 解读 何钦铭， 陆汉权， 冯博琴 330 2010 Towards automated reentrancy detection for smart contracts based on sequential models P Qian, Z Liu, Q He, R Zimmermann, X Wang IEEE access 8, 19685-19695 , 2020 248 2020 Smart contract vulnerability detection: from pure neural network to interpretable graph feature and expert pattern fusion Z Liu, P Qian, X Wang, L Zhu, Q He, S Ji arXiv preprint arXiv:2106.09282 , 2021 162 2021 Rethinking smart contract fuzzing: Fuzzing with invocation ordering and important branch revisiting Z Liu, P Qian, J Yang, L Liu, X Xu, Q He, X Zhang IEEE Transactions on Information Forensics and Security 18, 1237-1251 , 2023 134 2023 Performance measuring and comparing of virtual machine monitors J Che, Q He, Q Gao, D Huang 2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing�… , 2008 131 2008 虚拟化云计算平台的能耗管理 叶可江， 吴朝晖， 姜晓红， 何钦铭 计算机学报 35 (006), 1262-1285 , 2012 128 2012 Smart contract vulnerability detection technique: A survey P Qian, Z Liu, Q He, B Huang, D Tian, X Wang arXiv preprint arXiv:2209.05872 , 2022 125 2022 Behavior pattern clustering in blockchain networks B Huang, Z Liu, J Chen, A Liu, Q Liu, Q He Multimedia Tools and Applications 76 (19), 20099-20110 , 2017 124 2017 Fedrecattack: Model poisoning attack to federated recommendation D Rong, S Ye, R Zhao, HN Yuen, J Chen, Q He 2022 IEEE 38th International Conference on Data Engineering (ICDE), 2643-2655 , 2022 108 2022 Synthesis of Wafer-Scale Monolayer WS 2 Crystals toward the Application in Integrated Electronic Devices J Chen, K Shao, W Yang, W Tang, J Zhou, Q He, Y Wu, C Zhang, X Li, ... ACS applied materials & interfaces 11 (21), 19381-19387 , 2019 104 2019 Cross-modality mutual learning for enhancing smart contract vulnerability detection on bytecode P Qian, Z Liu, Y Yin, Q He Proceedings of the ACM web conference 2023, 2220-2229 , 2023 74 2023 Online e-commerce fraud: a large-scale detection and analysis H Weng, Z Li, S Ji, C Chu, H Lu, T Du, Q He 2018 IEEE 34th International Conference on Data Engineering (ICDE), 1435-1440 , 2018 72 2018 Mining regional co-location patterns with k NNG F Qian, K Chiew, Q He, H Huang Journal of Intelligent Information Systems 42 (3), 485-505 , 2014 72 2014 Poisoning deep learning based recommender model in federated learning scenarios D Rong, Q He, J Chen arXiv preprint arXiv:2204.13594 , 2022 65 2022 基于超文本结构的智能计算机辅助教学系统 陈颖， 何钦铭， 王申康 计算机研究与发展 35 (5), 442-446 , 1998 61 1998 Towards understanding the security of modern image captchas and underground captcha-solving services H Weng, B Zhao, S Ji, J Chen, T Wang, Q He, R Beyah Big Data Mining and Analytics 2 (2), 118-144 , 2019 55 2019 基于计算思维的 “大学计算机基础” 课程教学内容设计 陆汉权， 何钦铭， 徐镜春 中国大学教学 9, 55-58 , 2012 52 2012 人工智能基础 高济， 自动化， 朱淼良， 何钦铭 高等教育出版社 , 2002 51 2002 Virt-LM: a benchmark for live migration of virtual machine D Huang, D Ye, Q He, J Chen, K Ye Proceedings of the 2nd ACM/SPEC International Conference on Performance�… , 2011 50 2011 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=1Vitx-wAAAAJ&hl=ko&oe=ASCII | Hongbin Liu - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 전체 2021년 이후 서지정보 2080 2076 h-index 13 13 i10-index 15 15 0 1700 850 425 1275 2021 2022 2023 2024 2025 2026 9 67 124 204 1627 42 공개 액세스 모두 보기 모두 보기 자료 10개 자료 0개 공개 비공개 재정 지원 요구사항 기준 공동 저자 Neil Zhenqiang Gong Associate Professor, Duke University duke.edu의 이메일 확인됨 Jinyuan Jia Assistant Professor, Penn State psu.edu의 이메일 확인됨 Yupei Liu Penn State psu.edu의 이메일 확인됨 Lun Wang Google Deepmind google.com의 이메일 확인됨 Xiaoyu Cao PhD. Duke University duke.edu의 이메일 확인됨 Arun Narayanan Senior Staff Research Scientist at Google Deepmind google.com의 이메일 확인됨 Michael Reiter James B. Duke Distinguished Professor, Duke University duke.edu의 이메일 확인됨 Pedro J Moreno Mengibar, PhD Humain.ai Chief AI Scientist ieee.org의 이메일 확인됨 Abhradeep Guha Thakurta Google Research - Brain Team google.com의 이메일 확인됨 Om Thakkar Member of Technical Staff, OpenAI openai.com의 이메일 확인됨 팔로우 Hongbin Liu Google Deepmind google.com의 이메일 확인됨 - 홈페이지 Generative AI Security and Privacy AI Safety 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ... arXiv preprint arXiv:2507.06261 , 2025 1401 2025 Encodermi: Membership inference against pre-trained encoders in contrastive learning H Liu, J Jia, W Qu, NZ Gong Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications�… , 2021 130 2021 Pointguard: Provably robust 3d point cloud classification H Liu, J Jia, NZ Gong Proceedings of the IEEE/CVF conference on computer vision and pattern�… , 2021 113 2021 Visual Hallucinations of Multi-modal Large Language Models W Huang, H Liu, M Guo, NZ Gong Findings of the Association for Computational Linguistics (ACL) , 2024 92 2024 StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning Y Liu, J Jia, H Liu, NZ Gong ACM Conference on Computer and Communications Security (CCS) , 2022 70 2022 PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning H Liu, J Jia, NZ Gong USENIX Security Symposium , 2022 56 2022 Data Poisoning based Backdoor Attacks to Contrastive Learning J Zhang, H Liu, J Jia, NZ Gong Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern�… , 2024 39 * 2024 AudioMarkBench: Benchmarking Robustness of Audio Watermarking H Liu, M Guo, Z Jiang, L Wang, NZ Gong NeurIPS Datasets and Benchmarks 2024 , 2024 30 2024 Almost tight l0-norm certified robustness of top-k predictions against adversarial perturbations J Jia, B Wang, X Cao, H Liu, NZ Gong International Conference on Learning Representations (ICLR) , 2022 29 2022 Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning X He, H Liu, NZ Gong, Y Zhang European Conference on Computer Vision (ECCV) , 2022 27 2022 PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees J Zhang, J Jia, H Liu, NZ Gong IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2023 17 2023 10 Security and Privacy Problems in Large Foundation Models J Jia, H Liu, NZ Gong AI Embedded Assurance for Cyber Systems , 2023 15 * 2023 On the Intrinsic Differential Privacy of Bagging H Liu, J Jia, NZ Gong International Joint Conference on Artificial Intelligence (IJCAI) , 2021 15 2021 Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment Z Shao, H Liu, J Mu, NZ Gong ACM Workshop on Artificial Intelligence and Security (AISec) , 2025 12 * 2025 Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models H Liu, MK Reiter, NZ Gong USENIX Security Symposium , 2024 10 2024 Pre-trained encoders in self-supervised learning improve secure and privacy-preserving supervised learning H Liu, W Qu, J Jia, NZ Gong IEEE Security and Privacy Workshops , 2024 6 2024 Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning Y Jia, M Fang, H Liu, J Zhang, NZ Gong Conference on Neural Information Processing Systems (NeurIPS) , 2025 5 2025 Generation-based fuzzing? Don’t build a new generator, reuse! C Pang, H Liu, Y Wang, NZ Gong, B Mao, J Xu Computers & Security 129, 103178 , 2023 5 2023 Can DeepFake Speech be Reliably Detected? H Liu, Y Chen, A Narayanan, A Balachandran, PJ Moreno, L Wang arXiv preprint arXiv:2410.06572 , 2024 3 2024 Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models H Liu, L Wang, O Thakkar, A Thakurta, A Narayanan Conference of the International Speech Communication Association (Interspeech) , 2025 2 2025 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://opensource.guide/ko/how-to-contribute/ | 오픈소스에 기여하는 방법 | Open Source Guides 소개 기여 العربية Български Bangla Deutsch Ελληνικά English Español Farsi Français Hindi Magyar Indonesia Italiano 日本語 한국어 Malay Nederlands Pidgin Polski Português Romanian Русский संस्कृतम् Swahili தமிழ் Türkçe 简体中文 繁體中文 Open Source Guides 오픈소스에 기여하는 방법 오픈소스에 기여하고 싶으세요? 초보자와 숙련자를 위한 오픈소스 기여 가이드입니다. 목차 왜 오픈소스에 기여할까요? 기여한다는 것의 의미 새 프로젝트로 향하기 기여할 프로젝트 찾기 기여하는 방법 기여한 후에 일어나는 일 왜 오픈소스에 기여할까요? Working on [freenode] helped me earn many of the skills I later used for my studies in university and my actual job. I think working on open source projects helps me as much as it helps the project! — @errietta, “Why I love contributing to open source software” 오픈소스에 기여하는 것은 여러분이 상상할 수 있는 모든 기술을 배우고, 가르치고, 구현하는 보람찬 방법이 될 수 있습니다. 왜 사람들은 오픈소스에 기여할까요? 많은 이유가 있습니다! 기존 기술을 향상시키세요 코딩, 사용자 인터페이스 디자인, 그래픽 디자인, 글쓰기 또는 조직화 등의 실습을 원한다면 여러분이 맡을 수 있는 오픈소스 프로젝트 작업이 기다리고 있습니다. 비슷한 것에 관심 있는 사람들을 만나세요 따뜻한 커뮤니티가 있는 오픈소스 프로젝트는 사람들은 오래 머물게 합니다. 많은 사람들이 오픈소스에 참여하며 평생의 우정을 다지고 있습니다. 그게 회의에서 서로를 마주치는 것이든 한밤중에 부리토에 관해 채팅을 하는 것이든 상관없이요. 멘토를 찾고 사람들과 배움을 주고받으세요 공유 프로젝트에서 다른 사람들과 함께 일한다는 것은 여러분이 무엇을 어떻게 하는지 설명하고, 다른 사람들에게 도움을 요청해야 함을 의미합니다. 학습하고 가르치는 행위는 관련된 모든 사람들에게 성취감 있는 활동이 될 수 있습니다. 평판(과 경력)을 쌓는 데 도움이 되는 예제를 만드세요 정의에 따라 모든 오픈소스 저작물은 공개되어 있으므로, 당신이 할 수 있는 것을 보여줄 예제를 가질 수 있는 셈입니다. 사람을 대하는 기술을 습득하세요 오픈소스는 충돌 해결, 팀 구성, 작업 우선순위 지정과 같은 리더십 및 관리 기술을 연습할 수 있는 기회를 제공합니다. 작은 것조차도 바꿀 수 있는 힘이 있습니다 오픈소스에 참여하는 것을 즐기는 평생 기여자가 될 필요는 없습니다. 웹 사이트에서 오타를 발견하고 누군가가 고쳐주길 바란 적 있나요? 오픈소스 프로젝트에서 여러분은 그렇게 할 수 있습니다. 오픈소스는 사람들이 삶에 대해 어떻게 대처하고 그들이 세상을 경험하는지를 느끼도록 도와줍니다. 기여한다는 것의 의미 새로운 오픈소스 기여자라면, 기여하는 과정이 겁날 수도 있습니다. 알맞은 프로젝트를 어떻게 찾아야 할까요? 코딩을 할 줄 모른다면요? 뭔가 잘못되면 어떡하죠? 걱정 마세요! 오픈소스 프로젝트에 참여하는 데는 여러 가지 방법이 있으며, 몇 가지 팁을 통해 경험을 최대한 활용할 수 있습니다. 코드를 제공할 필요가 없습니다 오픈소스에 기여하는 것에 대한 일반적인 오해는 코드를 작성해야 한다는 것입니다. 사실, 프로젝트의 다른 부분이 무시되거나 간과되는 경우 가 더 많습니다. 이러한 유형의 기여에 동참하겠다고 제안하면 프로젝트에 큰 도움이 될 것입니다. I’ve been renowned for my work on CocoaPods, but most people don’t know that I actually don’t do any real work on the CocoaPods tool itself. My time on the project is mostly spent doing things like documentation and working on branding. — @orta, “Moving to OSS by default” 코드를 작성하는 것을 좋아해도, 다른 유형의 기여는 프로젝트에 참여하고 다른 커뮤니티 구성원을 만날 수 있는 좋은 방법입니다. 이러한 관계를 구축하면 프로젝트의 다른 부분에서 작업할 기회를 얻을 수 있습니다. 행사 계획 짜는 걸 좋아하세요? NodeSchool을 위해 @fzamperin이 했던 것처럼 , 프로젝트에 관한 워크샵이나 미팅 조직하기 프로젝트 컨퍼런스 구성하기 (있는 경우) 커뮤니티 구성원이 적합한 컨퍼런스를 찾고 발언을 위한 제안서를 제출할 수 있도록 지원하기 디자인을 하고 싶으세요? 프로젝트의 유용성을 높이기 위해 레이아웃 재구성하기 Drupal의 제안 처럼, 사용자 조사를 통해 프로젝트의 네비게이션 또는 메뉴를 재구성하고 개선하기 프로젝트가 일관성 있는 시각적 디자인을 가질 수 있도록 스타일 가이드 작성하기 hapi.js의 기여 처럼, 티셔츠 혹은 새로운 로고를 위한 예술 작품 만들기 글을 쓰고 싶으신가요? 프로젝트 문서 작성 및 개선하기 프로젝트 사용법을 보여주는 예제 폴더 선별하기 프로젝트의 뉴스레터 발행을 시작하거나 메일링 리스트의 하이라이트를 관리하기 PyPA의 기여처럼 , 프로젝트 튜토리얼 작성하기 프로젝트 문서 번역 작성하기 Seriously, [documentation] is mega-important. The documentation so far has been great and has been a killer feature of Babel. There are sections that could certainly use some work and even the addition of a paragraph here or there is extremely appreciated. — @kittens, “Call for contributors” 조직하는 것을 좋아하세요? 중복된 이슈에 대한 링크 및 새로운 이슈 라벨 제안, 정리된 상태 유지하기 ESLint의 @nzakas 처럼, 열려있는 이슈를 검토하고 오래된 이슈를 닫을 것을 제안하기 최근 열린 이슈에 대한 질문을 명확히 하여 토론으로 나아가게 하기 코드를 작성하고 싶으세요? Leaflet의 @dianjin처럼 , 해결할 문제를 찾기 새로운 기능을 작성하는 데 도움을 줄 수 있는지 물어보기 프로젝트 설정 자동화하기 툴링 및 테스트 개선하기 사람들을 돕는 것을 좋아하세요? Stack Overflow( Postgres 예시 ) 혹은 Reddit에서 프로젝트에 관련된 질문에 답변하기 열린 이슈에서 사람들의 질문에 답변하기 토론 게시판이나 대화 채널 관리 돕기 사람들의 코드 작성을 돕고 싶으세요? 사람들이 제출한 코드 리뷰하기 프로젝트를 어떻게 이용하는가에 대한 튜토리얼 작성하기 Rust의 @ereichert가 @bronzdoc에게 해준 것처럼 , 다른 기여자의 멘토가 되는 것을 제안하기 꼭 소프트웨어 프로젝트에서 작업할 필요는 없습니다! “오픈소스”는 보통 소프트웨어를 의미하지만, 무엇이든 간에 거의 협력할 수 있습니다. 오픈소스 프로젝트로 개발되는 책, 요리법, 리스트 및 수업도 있습니다. 예를 들면: @sindresorhus는 list of “awesome” lists 를 만들었습니다 @h5bp는 프론트엔드 개발자 후보군용 list of potential interview questions 을 관리하고 있습니다 @stuartlynn과 @nicole-a-tesla는 collection of fun facts about puffins 를 만들었습니다 비록 당신이 소프트웨어 개발자일지라도, 문서 프로젝트 작업은 오픈소스에서 시작하는 데 도움이 될 수 있습니다. 코드를 포함하지 않는 프로젝트에서 작업하는 것은 보통 어렵지 않으며, 협력하는 과정에서 여러분의 자신감과 경험을 쌓을 수 있을 것입니다. 새 프로젝트로 향하기 If you go to an issue tracker and things seem confusing, it’s not just you. These tools require a lot of implicit knowledge, but people can help you navigate it and you can ask them questions. — @shaunagm, “How to Contribute to Open Source” 오타를 수정하는 것 이상으로 오픈소스에 기여하는 것은 파티에서 낯선 사람들에게 다가가는 것과 같습니다. 사람들이 금붕어에 대한 깊은 토론에 빠져 있을 때 라마에 대해 이야기한다면 그들은 아마 여러분을 약간 이상하게 볼 겁니다. 맹목적으로 여러분의 제안을 펼치기 전에, 방의 분위기를 읽는 법을 배우는 것부터 시작하세요. 그러면 여러분의 아이디어에 귀 기울여 줄 가능성이 높아집니다. 오픈소스 프로젝트의 해부학 모든 오픈소스 커뮤니티는 서로 다릅니다. 여러 해 동안 한 오픈소스 프로젝트에 투자했다면 그 프로젝트를 잘 알게 됐을 것입니다. 다른 프로젝트로 넘어가면 어휘, 표준, 커뮤니케이션 스타일이 완전히 다르다는 것을 알 수 있습니다. 많은 오픈소스 프로젝트는 비슷한 조직 구조를 따릅니다. 다양한 커뮤니티 역할과 전반적인 프로세스를 이해하면 새로운 프로젝트에 빠르게 적응할 수 있습니다. 일반적인 오픈소스 프로젝트에서 사람들은 다음과 같은 유형으로 나뉩니다. 작성자: 이 프로젝트를 만든 사람 혹은 조직 소유자: 조직 또는 저장소에 대한 관리 권한을 가진 사람 (항상 원래 작성자와 동일하지는 않음) 메인테이너: 비전을 주도하고 프로젝트의 조직 측면을 관리하는 책임이 있는 기여자 (그들은 프로젝트의 저자 또는 소유자일 수도 있습니다.) 기여자: 프로젝트에 기여한 모든 사람. 커뮤니티 맴버: 프로젝트를 사용하는 사람들. 적극적으로 대화에 참여하거나 프로젝트 방향에 대한 의견을 제시할 수도 있습니다. 더 큰 프로젝트에는 툴링, 선별, 커뮤니티 중재 및 이벤트 조직과 같은 다양한 업무에 초점을 둔 소위원회 또는 실무 그룹이 있을 수도 있습니다. 프로젝트 웹 사이트에서 “팀” 페이지를 찾거나 거버넌스 문서 저장소에서 정보를 찾아보세요. 프로젝트에도 문서가 있습니다. 이러한 파일은 대개 저장소의 최상위 레벨에 나열됩니다. LICENSE: 정의에 의해, 모든 오픈소스 프로젝트는 반드시 오픈소스 라이선스를 가져야 합니다 . 만약 프로젝트가 라이선스를 가지지 않는다면, 이건 오픈소스가 아닙니다. README: README는 새로운 커뮤니티 구성원을 프로젝트에 환영하는 지침서입니다. 왜 프로젝트가 유용한지, 어떻게 시작해야 할지 설명합니다. CONTRIBUTING: README는 사람들이 프로젝트를 사용하는 데 도움이되지만, CONTRIBUTING 문서는 사람들이 프로젝트에 _기여_하는 데 도움이 됩니다. 필요한 기여 유형과 프로세스 작동 방식을 설명합니다. 모든 프로젝트가 CONTRIBUTING 파일을 갖고 있는 것은 아니지만, 이 파일이 있다면 여러분의 기여를 환영한다는 뜻입니다. CODE_OF_CONDUCT: Code of Conduct(윤리 강령)는 참가자의 행동에 대한 기본 원칙을 정하고, 친절하고 따뜻한 환경을 조성하는 데 도움이 됩니다. 마찬가지로 모든 프로젝트가 CODE_OF_CONDUCT 파일을 가지고 있지는 않지만, 이 파일이 있다면 여러분의 기여를 환영한다는 뜻입니다. 다른 문서: (특히 큰 프로젝트의 경우) 튜토리얼, 연습장 또는 거버넌스 정책과 같은 추가 문서가 있을 수 있습니다. 마지막으로 오픈소스 프로젝트는 다음 도구를 사용하여 토론을 구성합니다. 기록 보관소를 읽으면 커뮤니티가 어떻게 사고하고 작동하는지 잘 알 수 있습니다. Issue tracker: 프로젝트와 관련된 이슈를 토론하는 공간입니다. Pull requests: 지금 진행 중인 변경 사항에 대해 논의하고 검토하는 공간입니다. 토론 포럼 혹은 메일링 리스트: 일부 프로젝트는 회화성 주제(버그 제보나 기능 요구 대신 “…하려면 어떻게 하나요?” 또는 “…에 대해 어떻게 생각하세요?” 같은 주제)에 대해 이러한 채널을 사용할 수 있습니다. 나머지 프로젝트는 모든 대화에 이슈 트래커를 사용합니다. 채팅 채널: 일부 프로젝트에서는 일상 대화, 협업 및 빠른 의사소통을 위해 Slack이나 IRC 같은 채팅 채널을 사용합니다. 기여할 프로젝트 찾기 오픈소스 프로젝트가 어떻게 작동하는지 알았으니, 이제 기여할 프로젝트를 찾아야 합니다! 이전에 오픈 소스에 기여한 적이 없다면, 미국 존 케네디 대통령의 명언을 떠올려보세요. “Ask not what your country can do for you - ask what you can do for your country.” “국가가 나를 위해 무엇을 해줄 것을 바라기에 앞서, 내가 국가를 위해 무엇을 할 것인가를 생각해야 한다.” 오픈소스에 기여하는 것은 프로젝트 전반에 걸쳐 모든 수준에서 발생합니다. 여러분의 첫 번째 기여가 정확히 무엇이고 어떻게 보일지 생각할 필요가 없습니다. 대신, 이미 사용하고 있거나 사용하고 싶은 프로젝트에 대해 생각하는 것으로 시작하세요. 여러분이 적극적으로 기여하게 될 프로젝트는 여러분이 계속 사용하게 되는 프로젝트입니다. 그 프로젝트에서, 뭔가가 더 좋거나 다를 수 있다고 생각할 때마다 본능에 따라 행동하세요. 오픈소스는 독점적인 클럽이 아닙니다. 여러분과 같은 사람들에 의해 만들어졌습니다. “오픈소스”는 전세계의 문제들을 유연하게 해결할 수 있는 멋진 용어입니다. README를 스캔하여 깨진 링크나 오타를 찾을 수 있습니다. 또는 여러분이 새로운 사용자로서 제대로 동작하지 않거나 문서에서 다뤄져야 할 이슈를 발견할 수도 있습니다. 그것을 무시하거나 다른 사람에게 그것을 고쳐달라고 하는 대신, 여러분이 직접 도움을 줄 수 있는지 알아보세요. 그것이 바로 오픈소스입니다! 일반적인 기여의 28% 는 오타 수정, 서식 재지정 또는 번역 작성과 같은 문서입니다. 다음 리소스 중 하나를 사용하여 새 프로젝트를 찾고 기여할 수 있습니다. GitHub Explore Open Source Friday First Timers Only CodeTriage 24 Pull Requests Up For Grabs First Contributions SourceSort OpenSauced 기여하기 전 확인할 사항 기여하고 싶은 프로젝트를 찾았으면, 프로젝트가 기여를 받기에 적합한지 빠르게 확인하세요. 그렇지 않으면, 노력이 영원히 응답을 받지 못할 수도 있습니다. 다음은 프로젝트가 새로운 기여자에게 적합한지 평가할 수 있는 편리한 체크리스트입니다. 오픈소스의 정의를 충족시킬 것 라이선스가 있나요? 대부분, 저장소의 최상단에 있는 LICENSE라 불리는 파일입니다. 프로젝트가 적극적으로 기여를 받아들일 것 마스터 브랜치에서 커밋 활동을 살펴보세요. GitHub에서는 이 정보를 저장소의 홈페이지에서 볼 수 있습니다. 마지막 커밋은 언제였나요? 몇 명의 기여자가 프로젝트에 참여했나요? 사람들이 얼마나 자주 커밋하나요? (GitHub에서는 상단 바에 있는 "Commits"를 클릭하면 볼 수 있습니다.) 다음으로, 프로젝트의 이슈를 보세요. 얼마나 많은 열린 이슈가 있나요? 관리자가 열린 이슈에 신속하게 대응하나요? 이슈에 대한 활발한 토론이 있나요? 최근에 이슈가 있나요? 이슈가 닫히고 있나요? (GitHub에서는, Issues 페이지에서 닫힌 이슈를 "closed" 탭을 눌러 볼 수 있습니다.) 이번엔 프로젝트의 풀 리퀘스트(PR)를 확인하세요. 얼마나 많은 PR이 열려 있나요? 관리자가 열린 PR에 신속하게 대응하나요? PR에서 활발한 토론이 진행되나요? 최근에 PR이 있나요? 최근에 PR이 병합된 건 언제인가요? (GitHub에서는, Pull requests 페이지에서 "closed" 탭을 눌러 닫힌 PR을 볼 수 있습니다.) 프로젝트가 기여자를 환영할 것 친근하고 환영하는 분위기의 프로젝트는 새로운 기여자를 기꺼이 맞이합니다. 관리자가 이슈의 질문에 도움이 되는 답변을 주나요? 이슈, 토론 포럼 및 채팅(IRC 혹은 Slack 등)에 있는 사람들이 친절한가요? PR이 리뷰를 받고 있나요? 관리자가 기여자들에게 감사를 표하고 있나요? Whenever you see a long thread, spot check responses from core developers coming late in the thread. Are they summarizing constructively, and taking steps to bring the thread to a decision while remaining polite? If you see a lot of flame wars going on, that’s often a sign that energy is going into argument instead of into development. — @kfogel, Producing OSS 기여하는 방법 기여하고 싶은 프로젝트를 찾았나요? 드디어! 기여하는 올바른 방법은 다음과 같습니다. 효과적으로 의사소통하기 하나의 기여를 하든 커뮤니티에 참여하려고 하든, 관계없이 다른 사람들과 협력하는 것은 오픈소스에서 개발할 가장 중요한 기술 중 하나입니다. [As a new contributor,] I quickly realized I had to ask questions if I wanted to be able to close the issue. I skimmed through the code base. Once I had some sense of what was going on, I asked for more direction. And voilà! I was able to solve the issue after getting all the relevant details I needed. — @shubheksha, A Beginner’s Very Bumpy Journey Through The World of Open Source 이슈나 PR을 열거나 채팅에서 질문을 하기 전에 아이디어를 효과적으로 전달할 수 있도록 아래와 같은 사항을 명심하세요. 맥락을 제공하세요. 다른 사람들이 빨리 속도를 낼 수 있도록 도와주세요. 오류가 발생하면 수행하려는 작업과 오류를 재현하는 방법을 설명하세요. 새로운 아이디어를 제안하는 경우 그것이 (여러분이 아닌) 프로젝트에 유용하다고 생각하는 이유를 설명하세요. 😇 “Y를 할 때 X가 안 돼요.” 😢 “X가 안 돼요! 이거 고쳐주세요.” 과제를 미리 하세요. 이해하지는 못하지만 시도해봤다는 것을 보여주세요. 도움을 요청하기 전에 프로젝트의 README, 문서, (열린 혹은 닫힌) 이슈, 메일링 리스트를 확인하고 인터넷에서 해결책을 검색해보세요. 당신이 배우려는 자세를 보이면 사람들은 존중할 것입니다. 😇 “X를 구현하는 방법을 잘 모르겠어요. 도움말 문서를 확인했지만 관련 언급을 찾지 못했어요.” 😢 “X는 어떻게 해요?” 짧고 직접적으로 요청하세요. 이메일을 보내는 것과 마찬가지로, 모든 기여는 아무리 간단하거나 도움이 된다 하더라도 다른 사람의 검토가 필요합니다. 많은 프로젝트가 사람들이 도울 수 있는 것보다 많은 요청을 받고 있습니다. 간결하게 적으세요. 누군가 당신을 도울 가능성이 늘어날 것입니다. 😇 “API 튜토리얼을 작성하고 싶어요.” 😢 “요전날 고속도로를 따라 차를 몰고 가다가 주유소에 들렀는데, 우리가 해야 할 일에 대한 놀라운 아이디어가 떠올랐어요. 하지만 설명해드리기 전에 보셔야 할 게 있는데요…” 모든 의사소통을 공개하세요. 매혹적이긴 하지만 보안 문제나 심각한 규칙 위반 같은 중요한 정보를 공유해야 하는 경우가 아니면 관리자에게 개인적으로 연락하지 마세요. 대화를 공개해야 더 많은 사람들이 여러분의 교류를 통해 배우고 이익을 얻을 수 있습니다. 토론은 그 자체로 기여가 됩니다. 😇 (댓글로) “@-관리자 안녕하세요! 이 PR은 어떻게 진행되고 있나요?” 😢 (이메일로) “안녕하세요, 메일로 귀찮게 해서 죄송합니다만 제 PR을 검토해보셨는가 해서요.” 질문하는 것은 좋지만 참을성을 가지세요. 누구나 프로젝트를 처음 접했을 때가 있으며 경험 많은 기여자도 새로운 프로젝트에는 가속이 필요합니다. 마찬가지로 오랜 관리자도 프로젝트의 모든 부분을 항상 잘 알고 있는 것은 아닙니다. 여러분이 기대하는 만큼의 인내심을 사람들에게 보여주세요. 😇 “이 오류를 알아봐 주셔서 감사합니다. 제안을 따라 고쳐 봤어요. 이렇게 출력되네요.” 😢 “왜 이 문제를 해결할 수 없는 거죠? 이 프로젝트는 관리자님이 만든 게 아닌가요?” 커뮤니티의 결정을 존중하세요. 여러분의 아이디어는 커뮤니티의 우선순위나 비전과 다를 수 있습니다. 그들은 개선점을 제시하거나 여러분의 아이디어를 도입하지 않기로 결정할 수 있습니다. 절충안을 논의하는 동안 관리자는 여러분보다 오래 여러분의 결정을 고려해야 합니다. 여러분이 커뮤니티의 비전에 동의하지 않는다면 여러분의 포크에서 작업하거나 따로 프로젝트를 시작하는 방법도 있습니다. 😇 “제 유즈케이스를 지원할 수 없다는 점은 아쉽지만 일부 사용자에게만 영향을 미친다는 관리자님의 설명은 이해가 되네요. 들어주셔서 감사합니다.” 😢 “왜 제 유즈케이스를 지원하지 않나요? 납득할 수가 없네요!” 무엇보다도 세련된 자세를 유지하세요. 오픈소스는 전 세계의 협력자로 구성되어 있습니다. 맥락은 언어, 문화, 지역, 시간대에 걸쳐 점점 손실됩니다. 게다가 글을 통한 의사소통은 말투나 분위기를 전달하기가 어렵습니다. 대화에 좋은 의도를 가지고 참여한다고 생각하세요. 예의를 갖추면 아이디어를 밀어붙여도, 더 자세한 설명을 요구해도, 여러분의 입장을 명확히 해도 좋습니다. 다만 인터넷 세계를 여러분의 첫인상보다 좋은 곳으로 만들어 주세요. 정보 수집 무언가 시작하기 전에, 여러분의 아이디어가 다른 곳에서 논의되지 않았는지 빠르게 확인해 보세요. 프로젝트의 README, 이슈, 메일링 리스트 및 스택 오버플로우를 훑어보세요. 모든 것을 찾아보는 데 몇 시간을 투자할 필요는 없지만, 몇 가지 핵심 용어에 대한 검색이면 충분할 것입니다. 다른 곳에서 여러분의 아이디어를 찾을 수 없다면, 움직일 때가 되었습니다. 프로젝트가 GitHub에 있는 경우 다음과 같이 이슈나 PR을 열어 소통할 수 있습니다. 이슈 는 대화나 토론을 시작하는 것과 같습니다. 풀 리퀘스트 는 솔루션에 대한 작업을 시작하기 위한 것입니다. 명확한 질문이나 방법 질문과 같은 간단한 커뮤니케이션 은 스택 오버플로우 또는 IRC, 슬랙 같은 프로젝트 채팅 채널에 물어보세요. 이슈나 PR을 열기 전에 프로젝트의 기여 문서(일반적으로 CONTRIBUTING 또는 README 파일)에서 뭔가 구체적인 내용을 포함해야 하는지 확인하세요. 프로젝트에서 여러분에게 특정 템플릿을 따르거나 테스트를 사용하도록 요구할 수 있습니다. 실질적인 기여를 하고 싶다면, 작업하기 전에 이슈를 열고 물어보세요. 승인되지 않을 수도 있는 작업을 하기 전에(깃허브에서는, “Watch”를 클릭 해서 토론을 알림 받을 수 있습니다), 커뮤니티 구성원들을 알게 되면 도움이 됩니다. You’ll learn a lot from taking a single project you actively use, “watching” it on GitHub and reading every issue and PR. — @gaearon on joining projects 이슈 열기 일반적으로 다음 상황에서 이슈를 열어야 합니다. 스스로 해결할 수 없는 오류 보고 커뮤니티, 비전, 정책 등 높은 수준의 주제 또는 아이디어 토론 새로운 기능이나 다른 프로젝트 아이디어 제안 이슈에서 소통할 때의 팁은 다음과 같습니다. 열린 이슈에 대해 작업하려고 한다면 사람들이 알 수 있게 댓글을 달아두세요. 그렇게 하면 다른 사람과 같은 부분을 작업할 가능성이 줄어듭니다. 이슈가 오래 전부터 열려 있었다면 내용이 다른 곳에서 논의되고 있거나 이미 해결됐을 수도 있으므로 작업을 시작하기 전에 확인을 요청하세요. 이슈를 열었지만 나중에 해결법을 알아냈다면 이슈에 댓글을 달아 사람들에게 알리고 이슈를 닫으세요. 그 결과에 대한 문서화도 프로젝트에의 기여가 됩니다. PR 열기 일반적으로 다음 상황에서 PR을 열어야 합니다. 오타, 깨진 링크, 명백한 오류 등 사소한 수정 사항 제출 요구되고 있거나 이슈에서 논의한 내용에 대한 작업 시작 PR이 반드시 완료된 작업을 포함할 필요는 없습니다. 보통 다른 사람들이 여러분의 진행 상황을 확인하거나 피드백을 줄 수 있도록 PR을 일찍 여는 것이 좋습니다. 제목 줄에 “WIP”(Work In Progress; 진행 중인 작업)라고 표시하세요. 나중에 얼마든지 커밋을 더 추가해도 됩니다. 프로젝트가 GitHub에 있는 경우 PR을 제출하는 방법은 다음과 같습니다. 저장소를 포크 하고 로컬에 복제(Clone)합니다. 리모트로 추가하여 로컬을 원래의 “업스트림” 저장소에 연결하세요. PR을 제출할 때 충돌이 발생할 가능성을 낮추기 위해 “업스트림”의 변경 사항을 자주 가져 와서 최신 상태로 유지하세요. (자세한 내용은 여기 를 참조하세요.) 수정을 위한 브랜치를 생성 하세요. 모든 관련 이슈 혹은 지원 문서를 참조하세요. (ex. “Closes #37.”) 변경 사항에 HTML/CSS가 포함되어 있는 경우 적용 전/후 스크린샷을 첨부 하세요. PR의 본문에 이미지를 끌어다 놓으면 됩니다. 변경 사항을 테스트 하세요! 변경 사항에 대해 이미 있는 테스트를 수행하고 필요한 경우 새 테스트를 작성하세요. 테스트의 존재 여부와 상관없이 변경 사항이 기존 프로젝트를 손상시키지 않는지 확인하세요. 최선을 다해 프로젝트 스타일에 기여 하세요. 들여쓰기, 세미콜론 또는 주석을 여러분의 평소 스타일과 다르게 사용해야 할 수도 있지만, 관리자가 PR을 병합하기 더 용이하고 향후의 유지보수가 쉬워질 것입니다. 만약 첫 PR을 열려고 한다면 @kentcdodds가 무료 영상 튜토리얼로 공개한 Make a Pull Request 를 참조하세요. @Roshanjossey의 First Contributions 저장소에서 연습해볼 수도 있습니다. 기여한 후에 일어나는 일 해내셨군요! 오픈소스 기여자가 되신 것을 축하드립니다. 앞으로도 많이 기여하실 수 있기를 바랍니다. 기여를 제출하면 다음 중 하나의 일이 일어날 것입니다. 😭 답변을 받지 못했어요. 기여하기 전에 활동의 징조가 있는지 프로젝트를 확인 했기를 바랍니다. 그러나 활발한 프로젝트에서도 기여가 반응을 얻지 못할 수도 있습니다. 일주일 넘게 답변을 받지 못했다면 누군가에게 검토를 부탁하며 공손하게 대응하는 것이 좋습니다. 여러분의 기여를 검토할 수 있는 적절한 사람의 이름을 안다면 골뱅이표(@)를 이용한 멘션으로 리뷰를 요청할 수 있습니다. 절대 그 사람에게 개인적으로 연락하지 마세요. 공개적인 의사소통은 오픈소스 프로젝트에서 필수적이라는 것을 기억하세요. 여러분이 예의 있게 행동했음에도 아무도 답변을 주지 않을 수도 있습니다. 기분이 좋지는 않겠지만 너무 낙담하지 마세요. 누구나 겪는 일입니다! 답변을 받지 못하는 데에는 어쩔 수 없는 개인적인 사정 등 다양한 이유가 있을 수 있습니다. 기여할 다른 방법이나 프로젝트를 찾아보세요. 다른 커뮤니티 구성원들이 참여하고 반응하기 전에 기여에 너무 많은 시간을 투자하지 않는 게 오히려 좋습니다. 🚧 기여에 대한 수정을 요청받았어요. 아이디어에 대한 피드백이든 코드의 수정이든 기여 내용을 수정해 달라는 요청을 받는 경우가 많습니다. 누군가 수정을 요청하면 적극적으로 그에 응답하세요. 그들은 여러분의 기여를 리뷰하기 위해 기꺼이 시간을 들였습니다. PR을 열고 내버려 두는 것은 좋지 않습니다. 어떻게 수정해야 할지 모르겠다면 문제에 대해 조사하고 필요한 경우 도움을 요청하세요. 대화가 몇 달 동안 진행되다가 상황이 변한 경우처럼, 더 이상 문제를 해결할 시간이 없다면 관리자에게 알리세요. 누군가 다른 사람이 기꺼이 작업을 맡아줄 지도 모릅니다. 👎 기여가 받아들여지지 않았어요. 여러분의 기여는 받아들여질 수도 있고 그렇지 않을 수도 있습니다. 이미 너무 많은 작업을 하지 않았으면 합니다. 왜 그것이 받아들여지지 않았는지 잘 모르겠다면 관리자에게 피드백과 설명을 요청하는 것이 합리적입니다. 그러나 궁극적으로는 이것이 그들의 결정이라는 것을 존중할 필요가 있습니다. 논쟁하거나 적대적인 태도를 취하지 마세요. 동의하지 않으면 언제든 여러분의 버전을 포크하고 따로 작업할 수 있습니다! 🎉 기여가 받아들여졌어요. 만세! 오픈소스에 기여하는 데 성공했습니다! 해냈어요! 처음으로 오픈소스에 기여한 사람이든, 기여할 새로운 방법을 찾고 있든, 이 문서가 그것을 행동에 옮길 수 있는 계기가 되었길 바랍니다. 비록 기여가 받아들여지지 않더라도, 관리자가 당신을 도우려 할 때 감사의 말을 하는 것을 잊지 마세요. 오픈소스의 이슈, PR, 댓글 하나하나는 여러분에 의해 만들어집니다. 모든 가이드로 돌아가기 관련 가이드 오픈소스 프로젝트 시작하기 오픈소스의 세계에 대해 자세히 알아보고 여러분의 프로젝트를 시작할 준비를 해보세요. 마음을 끄는 커뮤니티 만들기 사람들이 프로젝트를 사용하고, 기여하고, 전파하도록 격려하는 커뮤니티를 만드세요. Scroll to Top 기여 제안을 하고 싶으신가요? 이 사이트는 오픈소스입니다. 개선할 수 있도록 도와주세요. 기여하기 구독 GitHub의 최신 오픈소스 팁과 리소스 관련 소식을 누구보다 먼저 들어보세요. 이메일 주소 fine print 와 친구 의 을 담은 | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/categories/business-management-software | Best Business Management Software | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Owner (79) Chief Executive Officer (61) Project Manager (52) Chief Financial Officer (37) Accountant (30) See all products Find top products in Business Management Software category Software used to oversee a range of core business processes on a single platform. - Automate day-to-day tasks involving accounting, customer relations, human resources, inventory, and reporting - Use integrations with existing business software to facilitate data sharing and higher-level planning - Consolidate operations for more efficient workflow 739 results Odoo Business Management Software by Odoo Odoo is a suite of open source business apps that cover all your company needs: CRM, eCommerce, accounting, inventory, point of sale, project management, etc. Odoo's unique value proposition is to be at the same time very easy to use and fully integrated. View product Zoho One Business Management Software by Zoho A unified suite of over 45+ apps, covering every function your business needs. Zoho One is an unbelievable, hassle-free offering that dissolves silos and lets information flow across your organization. View product Microsoft Dynamics 365 Business Central Business Management Software by Microsoft Dynamics 365 Streamline, manage, and grow your business with Dynamics 365 Business Central - a flexible, scalable, comprehensive business management solution for small and medium-sized businesses. View product Odoo Projects Business Management Software by Odoo Instantly improve your organization, scheduling, and planning skills with the Odoo Projects app. No other application offers such a clean and efficient overview of every detail surrounding your projects. With Odoo Projects, you can easily keep track of deadlines, and accurately allocate the necessary time needed for specific tasks under a planned shift. This not only saves you time and money, it streamlines the entire process, thus making your projects more efficient than ever. Managing your teams across various projects is now super simple, thanks to Odoo. With the ability to quickly compare project performance and employee availability, you’ll be able to increase profits and boost productivity. Odoo also allows you to easily break down your project into bite-sized tasks, which you can assign to any member of your team. You can even create and customize stages for each project. Odoo Projects is a flexible management software that's specifically designed to make everything easy! View product TallyPrime Business Management Software by Tally Solutions Pvt Ltd At Tally, we believe in the power of technology to make business owners efficient, empowered and happier, so they can focus on what matters most for their business. We design our products to focus on just that – to make our products work for you, and not the other way around. Our new product TallyPrime takes this to a new level, making your start to automation, or your switch to Tally simpler than ever before. You can now discover the product much more easily and make the product do more for you, without learning anything new. There is greater flexibility as the product adapts to your business and your way of working. And the transformed look and feel will only make you love the product even more. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights B2B Price AI by BCG X Business Management Software by BCG X B2B Price AI is a holistic and integrated solution that optimizes list price management and net price management. This AI-powered solution combines expert insight with the latest data to deliver customized pricing recommendations for your customers—generating 1-5+ pp margin uplift. View product Intelligent Enterprise Business Management Software by Celebal Technologies Intelligent Enterprise helps you be ahead of the game by bringing together all supply chain business units into a connected, cloud-based, advanced analytics platform. It is a supply chain management and analytics tool, built natively on Azure Cloud, leveraging Azure Data Lake on Synapse, Azure ML & Power BI. The solution comprises end-to-end supply chain management from demand sensing, production planning to distribution and logistics control towers. It also offers a Digital Sales and Operation planning built on Power BI and fully integrated with leading ERP solutions like SAP. Modules: • SAP Data Lake/Data Warehouse on Azure Synapse • Intelligent Demand Sensing • Trade Promotion Offer Analytics • Integrated Forecasting and Replenishment • S&OP on Microsoft Power BI • Intelligent Territory Engagement • Customer Insights • Product to Product Cannibalization • Constraint-based Optimization • Pricing Analytics View product IBM Apptio Costing Business Management Software by Apptio, an IBM Company IBM Apptio Costing delivers a clear, easy-to-understand view of an organization's diverse and evolving tech costs, facilitating impactful discussions across the business and driving informed decisions in a rapidly changing tech landscape. Apptio’s industry-leading allocation strategies tackle the difficult task of bringing together financial and operational data into a common, centralized framework, providing transparency on key spend drivers tied to business priorities, enabling leaders to focus on business outcomes and the value of each dollar spent, rather than chasing down data or constantly updating spreadsheets. View product SS&C Chorus Business Management Software by SS&C Technologies Built on SS&C’s reputation as an end-to-end solutions provider, SS&C Chorus brings together leading-edge intelligent automation technologies working in unison to create transformational, ROI-driven client solutions. Chorus optimizes smart technology, such as machine learning, robotic process automation and natural language processing to help customers transform and manage their business processes at scale. SS&C Chorus is delivered via SS&C’s secure private cloud, on premise and through public cloud offerings. View product BizTalk360 Business Management Software by Kovai.co One Platform. Operations, Monitoring, and Analytics for Microsoft BizTalk Server. On-Premise Solution for your BizTalk Server. BizTalk360 comes with 80+ features bundled into one single solution to help you monitor and administer your BizTalk Server environments. These features will enhance operational security, increase productivity, provide proactive alerting for issues and facilitate auto-healing. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:16 |
https://opensource.guide/fa/how-to-contribute/ | چگونه در یک پروژهی متن باز مشارکت کنیم | Open Source Guides درباره پروژه مشارکت العربية Български Bangla Deutsch Ελληνικά English Español Farsi Français Hindi Magyar Indonesia Italiano 日本語 한국어 Malay Nederlands Pidgin Polski Português Romanian Русский संस्कृतम् Swahili தமிழ் Türkçe 简体中文 繁體中文 Open Source Guides چگونه در یک پروژهی متن باز مشارکت کنیم میخواهید در یک پروژهی متن باز مشارکت کنید؟ در ادامهی مقاله نحوهی مشارکت در یک پروژهی متن باز برای افراد مبتدی و باتجربه شرح داده شده است. فهرست مطالب چرایی مشارکت در یک پروژهی متن باز؟ مشارکت به چه معناست؟ ورود و وفق دادن خودمان به یک پروژه جدید یافتن یک پروژه جهت مشارکت کردن در آن چگونه درخواست مشارکت را ارسال کنیم بعد از ارسال درخواست مشارکت چه اتفاقی میافتد چرایی مشارکت در یک پروژهی متن باز؟ کار کردن در Freenode به من در یادگیری بسیاری از مهارتها کمک کرد و توانستم از آنها در تحقیقات دانشگاهی و شغلم استفاده کنم. فکر میکنم به همان اندازه که کار کردن روی پروژههای متن باز به پیشبرد پروژه کمک میکند به همان اندازه به من هم کمک میکند! — @errietta, “Why I love contributing to open source software” زمانی که در پروژههای متن باز مشارکت میکنید، چیزهای زیادی یاد میگیرید یا یاد میدهید، حتی میتوانید در هر مهارتی که تصورش را میکنید تجربه کسب کنید. چرا افراد در پروژههای متن باز مشارکت میکنند؟ خب، دلایل زیادی وجود دارد! نرمافزاری که به آن متکی هستید را بهبود میدهید مشارکتکنندهها مشارکت خود از پروژههایی شروع میکنند که کاربر آن میشوند. زمانی که در نرمافزار یک پروژهی متن باز باگ یا خطایی مشاهده کردید، در صورتی که توانایی برطرف کردن آن را داشته باشید میتوانید به سورس کد آن نگاهی بیندازید و خودتان اصلاحیهای برایش بنویسید. اگر با چنین موردی روبهرو شدید، مشارکت در اصلاح آن باگ بهترین راه برای مطمئن کردن دوستان (و خودتان مخصوصاً زمانی که نسخهی بعدی آن به روز شود) باشد که میتواند مزیتهای داشته باشد. مهارتهای موجودتان تقویت میشود اگر به دنبال تمرین کدنویسی، طراحی رابطکاربری کاربر، طراحی گرافیک، نویسندگی یا سازماندهی کردن هستید، پروژهی متن باز این تمرینها را در اختیارتان قرار میدهد. با افرادی ملاقات میکنید که علایقشان با شما مشابه است پروژههای متن باز با انجمنهای گرم و گیرایش باعث میشود افرادی که در آن حضور دارند برای سالها به آن مراجعه کنند. حتی بسیاری هستند که به واسطهی همکاریشان در راهاندازی کنفرانسها یا چتهای آنلاین شبانهشان دربارهی burritos ، روابط دوستانهی طولانی مدتی دارند. استاد پیدا میکنید و به دیگران آموزش میدهید کار کردن با دیگران در پروژههای مشترک شما را مجبور میکند نحوهی انجام دادن کارها را توضیح دهید و به همان اندازه هم از دیگران کمک بخواهید. هر کسی میتواند خود را درگیرِ فعالیتهای یادگیری و آموزشی کند. محصولی عمومی تولید کنید که به رشد اعتبار و حرفهی کاریتان کمک کند بر اساس تعریف، تمام پروژههای متن باز شما عمومی هستند. به این معنا که نمونه پروژهها را دریافت میکنید و میتوانید آن را همه جا ببرید و نشان دهید که چه کارهایی میتوانید با آن انجام دهید. مهارتهای دیگران را یاد میگیرید پروژههای متن باز فرصتی فراهم میکنند که به واسطهی آن میتوانید مهارتهای مدیریت و رهبری پروژهی خود مانند برطرف کردن تضادها، سازماندهی کردن تیم و اولویت بندی کارها، را تقویت کنید. به شما قدرت اعمال تغییرات هرچند کوچک را میدهد لازم نیست برای لذت بردن از همکاری در یک پروژهی متن باز، به یک مشارکتکنندهی درازمدت تبدیل شوید. تا حالا شده در یک وبسایت چند غلط املائی ببینید و دوست داشتید یک نفر آن را اصلاح کند؟ خب، اگر چنین حالتی برای پروژهتان به وجود بیاید، به راحتی میتوانید آن را برطرف کنید. پروژهی متن باز میتواند به افراد کمک کند تا شرکتی که در آن فعالیت میکنند و نحوهی کسب کردن تجربهشان را از زندگی خود مهمتر بدانند و همین مسئله حس رضایتبخشی به آنها میدهد. مشارکت به چه معناست؟ اگر در مشارکت یک پروژهی متن باز تازهوارد هستید، فرآیند آن میتواند ترسناک باشد. شما چگونه یک پروژه درست برای مشارکت کردن در آن را انتخاب میکنید؟ اگر چیزی از کد نویسی ندانید، چی؟ اگر چیزی درست پیش نرود، چی؟ خب، نگران نباشید! راههای زیادی برای مشارکت در پروژههای متن باز وجود دارد که در ادامهی مقاله مواردی از آنها را میآوریم که میتواند به بدست آوردن تجربههای بیشتر به شما کمک کند. الزماً قرار نیست در فرایند کدنویسی مشارکت کنید یک دید غلط و مرسومی که برای مشارکت در پروژههای متن باز وجود دارد این است که فکر میکنند برای مشارکت در آن باید حتما کدنویسی شود. در حقیقت، اغلب بخشهای دیگر پروژه است که از آن غفلت یا بیش از حد به آن توجه میشود. شما با برطرف کردن مشکلات و مشارکت در آن بخشها لطف بزرگی به پروژههای متن باز میکنید. من شهرتم را از کار در CocoaPods به دست آوردم، اما بیشتر مردم نمیدانند که من واقعاً هیچ کار واقعی با ابزار CocoaPods انجام نمیدادم. زمانم در آن پروژه بیشتر روی چیزهایی مانند اسناد یا کار روی برندسازی صرف میشد. — @orta, “Moving to OSS by default” حتی اگر هم به کدنویسی در پروژه علاقهمند باشید، روشهای دیگر مشارکت بهترین راهبرای درگیر شدن در یک پروژه و ملاقات با اعضای انجمنهای دیگر وجود دارد. ساختن این روابط به شما فرصتهایی میدهد تا در بخشهای دیگر پروژه مشارکت کنید. آیا به برگزاری رویدادها علاقهمند هستید؟ ورکشاپها (کارگاهها) را سازماندهی یا جلسات پروژه را برگزار کنید، مانند کاری که @fzamperin برای NodeSchool انجام داد در صورت امکان، برای یک پروژه کنفرانس برگزار کنید به اعضای انجمن کمک کنید تا کنفرانسهای درستی پیدا و برای کنفرانس پرپوزال خود را ارسال کنند. آیا به طراحی علاقهمند هستید؟ با هدف افزایش قابلیت استفاده به بهبود ساختار برنامه ها کمک کنید. مشابه دروپال میتوانید با هدف بهبود رابط کاربری اقدام به کاربرپژوهی و مطالعاتی از این دست کنید. با جمع آوری و یک کاسه کردن الگوهای طراحی به کار گرفته شده در پروژه یک شیوهنامه (استایل گاید) متمرکز ایجاد کنید. اقدام به خلق کارهای هنری مثل طراحی لوگو یا تی شرت مخصوص کنید. مثل کاری که hapi.js انجام داد. آیا به نویسندگی در پروژه علاقهمند هستید؟ اسناد پروژه را بنویسید و اصلاح کنید پوشهی نمونهها را تنظیم کنید تا نحوهی استفادهی پروژه را نشان دهد برای پروژه یک خبرنامه راهاندازی کنید، یا شاخصههای آن را نوشته و تنظیم کنید برای پروژه، مطالب آموزشی بنویسید، مانند مشارکتکنندههایی که برای PyPA مطالب آموزشی نوشتند مستندات پروژه را به زبانی دیگر ترجمه کنید اسناد یک پروژه به طور جدی مهم هستند. اسناد پروژه تا به الان عالی پیش رفتند و یکی از ویژگیهای بینظیر Babel نیز بوده است. بخشهایی در اسناد یک پروژه وجود دارد که مطمئناً میتواند از آن در برخی کارها استفاده کرد، حتی افزودن یک پاراگراف در اینجا یا آنجا بینهایت قایل تقدیر است. — @kittens, “Call for contributors” آیا به سازماندهی پروژه علاقهمند هستید؟ برای سازماندهی کردن همه چیز، مشکلات تکراری را لینک کنید و مسائل جدیدی مطرح کنید با مسئلههای (issue) باز رودرو شوید و پیشنهاد دهید مسائل قدیمی حل شوند، مانند کاری که @nzakas برای ESLin انجام داد برای پیشبرد بحث، سوالات شفافی دربارهی مسائل باز اخیر بپرسید آیا به کدنویسی علاقه دارید؟ مسائل باز و حل نشده را پیدا و حل کنید، مانند کاری که @dianjin برای Leaflet انجام داد اگر میتوانید برای اعمال یک ویژگی جدید به پروژه کمک کنید، درخواستتان را مطرح کنید نصب پروژه را خودکار کنید ابزارهای مرتبط و تسهیل کننده و تست پروژه را تقویت کنید آیا از کمک کردن به مردم لذت میبرید؟ به سوالاتی که افراد دربارهی پروژه در سایتهایی مانند Stack، Postgres، یا Reddit میپرسند، جواب بدهید سوالات افرادی که مسائل حل نشدهای دارند را جواب بدهید در اداره کانالهای گفتگو و تالارهای گفتمان مشارکت کنید آیا دوست دارید در کدنویسی به دیگران کمک کنید؟ کدنویسی سایر افراد را بررسی کنید برای نحوهی استفادهی یک پروژهی متن باز، مطلب آموزشی بنویسید یک مشارکت کننده دیگر که میشناسید را پیشنهاد دهید، مثل کاری که @ereichert در Rust برای @bronzdoc کرد . لازم نیست فقط روی پروژههای نرمافزاری وقت صرف کنید! با اینکه بیشتر پروژههای متن باز به نرمافزارها اطلاق میشود، اما میتوانید هرچیزی از جمله کتابها، دستورالعمل، لیست چیزهای مختلف و کلاسها را در پروژههای متن باز توسعه دهید. به عنوان مثال: @sindresorhus لیستهایی موسوم به «awesome» گردآوری و تنظیم میکند @h5bp یک لیست حاوی سوالاتی جهت مصاحبه برای توسعه دهندگان فرانت اند را نگهداری و مرتب میکند @stuartivnn و @nicole-a-tesla مجموعهای از حقایق جالب دربارهی طوطی دریایی ایجاد کردهاند. حتی اگر توسعهدهندهی نرمافزار هم باشید، کار روی اسناد یک پروژه میتوانید به شما کمک کند تا پروژهی متن بازتان را شروع کنید. کار روی پروژههایی که کدنویسی کمتری دارد اغلب ترس کمتری دارد و فرآیند همکاری در آن باعث میشود اعتمادبهنفس و تجربهی شما افزایش پیدا کند. ورود و وفق دادن خودمان به یک پروژه جدید اگر به یک ایشو ترکر (issue tracker) برخوردید و چیزهای گیجکنندهای دیدید، نگران نباشید چون شما تنها نیستید. این ابزارها به دانش ضمنی زیادی نیاز دارند، اما سایرین میتوانند به شما کمک کند و میتوانید از آنها سوالاتی بپرسید. — @shaunagm, “How to Contribute to Open Source” مشارکت کردن در یک پروژهی متن باز که بیشتر از اصلاح غلطهایی املائی است، مانند وارد شدن به پارتی غریبههاست. اگر در این پارتی درباره ماهی قرمز بحث عمیقی شکل گرفته، شما دربارهی لاماها صحبت کنید، احتمالاً نگاه عجیبی به شما میشود. بنابراین، قبل از اینکه کورکورانه با پیشنهادهایتان وارد کاری شوید، یاد بگیرید که چگونه در چت رومها گفتگو کنید. این کار شانس شما را برای شنیده شدن و توجه به ایدههایتان را بالا میبرد. آناتومی یک پروژهی متن باز جامعهها در پروژههای متن باز متفاوت هستند. زمانی که سالها روی یک پروژهی متن باز صرف میکنید، باید آن پروژهی متن باز را بشناسید. از طرفی، زمانی هم که به پروژهی متفاوتی منتقل میشوید، لغات، قوائد و سبک ارتباطاتی آن که ممکن است کاملاً متفاوت باشد را باید پیدا کنید. گفته میشود بیشتر پروژههای متن باز از یک ساختار سازماندهی مشابه پیروی میکنند. شناخت و درک نقشها در جوامع مختلف و فرآیند کلی آن به شما کمک میکند به سرعت وارد هر پروژهی جدیدی شوید. افراد مختلفی در یک پروژهی متن باز معمولی مشارکت میکنند: نویسنده: شخص یا سازمانی که یک پروژه را خلق میکند صاحب مالک: شخص یا اشخاصی که صاحب اداری آن سازمان یا مخزن هستند (البته صاحب پروژه همیشه با نویسندهی اصلی یکسان نیست) مسئولنگهداری پروژه: مشارکتکنندههایی که مسئول پیش بردن چشم انداز و مدیریت جنبههای سازمانی یک پروژه باشند (این افراد همچنین میتوانند نویسنده یا صاحب پروژه باشند) مشارکتکننده: هر کسی که در پروژه مشارکت داشته باشد اعضای انجمن: افرادی که از پروژه استفاده میکنند، میتوانند مکالمات فعالانهای داشته باشند یا نظراتشان را برای مسیر دادن به پروژه ابراز کنند پروژههای بزرگتر همچنین ممکن است زیرکمیتهها یا گروههای کاری داشته باشند که روی وظایف متفاوتی مانند مجهز کردن، triage (تریاژ)، معتدل کردن انجمن و سازماندهی رویداد متمرکز میشوند. زمانی که به صفحهی «تیم» پروژهی یک وبسایت، یا مخزن مراجعه کنید، میتوانید اطلاعات این زیرکمیتهها و نقش افراد کلیدی را مشاهده کنید. پروژههای متن باز اسناد مختلفی دارند که این فایلها معمولا در بالای لیست مخزن قرار میگیرند. لایسنس/ گواهینامه (LICENSE): طبق تعریف، هر پروژهی متن بازی باید لایسنس مخصوص به خود را داشته باشد. اگر یک پروژه لایسنس نداشته باشد، اصلاً متن باز محسوب نمیشود فایل README: فایل README یک دستورالعمل ساختاری برای تمام اعضای جدید انجمن است که میتوانند آن را مطالعه میکنند. در این فایل به خوبی آورده شده که پروژهی در دست چه فوایدی دارد و چگونه باید از آن استفاده کرد فایل CONTRIBUTING: زمانی که یک فایل README میتواند به مردم برای استفاده از پروژه کمک کنند، فایل CONTRIBUTING هم میتواند برای مشارکت افراد در پروژه به شما و به آنها کمک کند. در این فایل توضیح داده شده که به چه نوع مشارکتی نیاز است و فرآیند کاری پروژه به چه نحوه است. با اینکه هر پروژه فایل CONTRIBUTING ندارد، اما در صورت وجود چنین فایلی در پروژه میتواند به افراد مختلف سیگنال مشارکت در پروژه بدهد. CODE_OF_CONDUCT: در فایل code of conduct میتوانید قوائدی که شرکتکنندگان باید با در نظر گرفتن آن به صورت دوستانه و راحت و در یک محیط پذیرا با سایرین برخورد کنند را بنویسید. با اینکه هر پروژه ممکن است حاوی این فایل نباشد، اما زمانی که یک پروژهی متن باز این فایل را داشته باشد، به مشارکتکنندهها این سیگنال را میفرستد میتوانند در پروژه مشارکت داشته باشند. این فایل تقریباً حاوی توصیههایی رفتاری برای تعامل است. اسناد دیگر: یک پروژهی متن باز به خصوص پروژههای بزرگتر ممکن است حاوی اسناد دیگری مانند فایلهای آموزشی، بازنگری فنی، راهنمای گام به گام (walkthroughs) ، یا سیاستهای دولتی باشند. در نهایت، پروژههای متن باز برای سازماندهی بحثها از ابزارهای زیر استفاده میکنند. مطالعهی آرشیو پروژهها میتواند دید خوبی از نحوهی فکر و کار انجمنها بدهد. ایشو ترکر (Issue tracker): جایی که افراد دربارهی مشکلات مرتبط با پروژه بحث میکنند درخواست Pull (Pull requests): جایی که افراد دربارهی تغییرات جاری بحث و بازبینی میکنند. انجمن گفتگو یا خبرنامه های ایمیلی: برخی از پروژه ها ممکن است برای موضوعات نیازمند بحث و گفتگو از انجمن های گفتگو یا خبرنامه ایمیلی به جای ایشو ترکر استفاده کنند. البته برخی دیگر ممکن است همین کار را به صورت کامل در بخش ایشو ترکر انجام دهند. Synchronous chat channel: بعضی از پروژههای از کانالهای چت مانند Slack یا IRC برای مکالمات محاورهای، همکاری یا تبادلات سریع استفاده میکنند. یافتن یک پروژه جهت مشارکت کردن در آن اکنون میدانید نحوهی کار یک پروژهی متن باز چگونه است. بنابراین، زمانش رسیده تا برای مشارکت، یک پروژهی متن باز پیدا کنید! اگر قبلا در هیچ پروژهی متن بازی مشارکت نداشتهاید، نصیحت رئیس جمهور آمریکا، جان. اف. کندی را بشنوید که گفت:«نگویید کشورتان برای شما چه کار کرده– بپرسید شما برای کشورتان چه کار کردهاید.» مشارکتکنندهها در تمام سطحهای میتوانند در پروژههای متن باز مشارکت کنند. لازم نیست بیش از حد به ذهن خود فشار بیاورید که اولین مشارکت شما در یک پروژه دقیقاً به چه صورت است، یا اولین مشارکتتان در آن پروژه چگونه خواهد شد. در عوض، به پروژههایی فکر کنید که قبلا استفاده شده، یا میخواهید استفاده کنید. پروژههایی که به صورت فعال در آن مشارکت میکنید، پروژههایی هستند که برمیگردند. هر زمان در چنین پروژههایی به این موضوع فکر کردید که میتوانستید بهتر از این یا متفاوتتر باشد، بهتر است از روی غریزه کار کنید. فکر نکنید یک پروژهی متن باز انحصاری است، چون پروژههای متن باز توسط افرادی مانند شما طراحی شده است. یک پروژهی متن باز تنها یک لفظ فانتزی برای برطرف کردن و حل مشکلات در دنیاست. شما در پروژههای متن باز میتوانید فایل README را مطالعه، لینکهای خراب و غلطهای املائی را پیدا و برطرف کنید. شما و کاربران جدیدتان هم میتوانند متوجه مشکل یا مسئلهای شوند که فکر کیکند باید از اسناد پروژه باشد. به جای نادیده گرفتن، عبور کردن یا سپردن آن مسائل به افراد دیگر، برای اصلاح آن مشکلات میتوانید کمک کنید. این تمام چیزی است که یک پروژهی متن باز میتواند داشته باشد! 28% از مشارکتکنندههای معمولی روی اسناد پروژهی متن باز مانند اصلاح غلطهای املائی، شکل دهی مجدد، یا نوشتن ترجمه مشارکت میکنند. اگر به دنبال مسائل موجود پروژهی متن بازتان هستید تا آن را برطرف کنید، میتوانید وارد صفحهی /contribute هر پروژهی متن باز شوید که مشکلات را برای تازهواردها برجسته میکند. شما میتوانید با حل کردن آن مشکلات، در مشارکت پروژهی متن باز همکاری داشته باشد. برای این منظور میتوانید به صفحهی اصلی repository (مخزن) در سایت GitHub مراجعه کنید و کلمهی /contribute را به انتهای آدرس URL آن اضافه کنید. به عنوان مثال: https://github.com/facebook/react/contribute ). شما همچنین میتوانید از منابع زیر برای کشف و مشارکت در پروژههای جدید کمک بگیرید: GitHub Explore Open Source Friday First Timers Only CodeTriage 24 Pull Requests Up For Grabs First Contributions SourceSort OpenSauced بررسی چک لیست قبل از مشارکت در پروژهی متن باز زمانی که پروژهی مورد علاقهتان برای مشارکت را پیدا کردید، نگاهی سریعی داشته باشید که آیا آن پروژه مناسب است تا درخواست همکاریتان را بفرستید. در غیر این صورت، کار پُرتلاش شما ممکن است هیچوقت به نتیجه نرسد. در ادامه میتوانید چک لیست دستی را ببینید که میتواند مشارکتکنندههای جدید یک پروژه را ارزیابی کند. پروژه با تعریف پروژهی متن باز مطابقت داشته باشد پروژهای که میخواهید در آن مشارکت کنید، لایسنس دارد؟ در هر پروژهی متن باز معمولاً فایلی با نام LICENSE در روت ریپاستوری (مخزن) آن وجود دارد پروژهی متن باز به صورت فعالانهای حضور مشارکتکنندهها را قبول میکند نگاهی به کامیت های اخیر در شاخه اصلی بیاندازید. در گیتهاب این این مورد در صفحه اصلی مخزن دیده میشود. آخرین کامیت چه زمانی بود؟ چه تعداد مشارکتکننده در پروژه حضور دارند؟ افراد چند بار کامیت میکنند؟ (در GitHub ، با کلیک روی «commits» روی بالای بار میتوانید آن را متوجه شوید.) در قدم بعدی به مسائل پروژه (issue) نگاهی بیندازید. چه تعداد مسائل حلنشده و باز در پروژه وجود دارد؟ آیا نگهدارندگان به موقع به مسائلی که مطرح میشوند واکنش نشان میدهند؟ آیا بحثها و گفتگوهای فعالی جهت حل مسائل وجود دارد؟ آیا اخیراً مسائلی گزارش شده است؟ مسائل پروژهی متن باز برطرف شدند؟ (میتوانید به صفحهی Issues در GitHub و تب «closed» مراجعه کنید تا مسائل حلشده را ببینید.) حالا، تمام این مراحل را برای درخواست ادغام یا Pull Request پروژه هم در نظر بگیرید. چه تعداد درخواست ادغام یا Pull Request در پروژه وجود دارد؟ آیا زمان دریافت درخواستهای ادغام، مسئولنگهداری به سرعت به آنها جواب میدهد؟ آیا بحثهای فعالی برای درخواستهای ادغام وجود دارد؟ آیا درخواستهای ادغام جدیدی در پروژه وجود دارد؟ جدیدترین درخواستهایی که ادغام شدن چه بودند؟ (میتوانید در صفحهی Pull Request و تب «closed» در سایت GitHub بروید تا درخواستهای ادغام انجام شده را ببینید پروژه پذیرای مشارکت است زمانی که یک پروژهی متن باز پذیرای مشارکتکنندههای جدید باشد، سیگنالهای دوستانهای برای مشارکتکنندهها میفرستد. آیا مسئول نگهداری جواب مفیدی به سوالات در بخش مسائل (Issues) میدهد؟ آیا افراد در صفحهی issue، تالارهای گفتگو، و صفحات چت مانند IRC یا Slack به طور دوستانهای رفتار میکنند؟ آیا درخواستهای ادغام بررسی میشوند؟ آیا مسئول نگهداری از افراد به خاطر مشارکتشان تشکر میکند؟ هر زمان که با یک موضوع طولانی روبهرو شدید، جوابهای توسعهدهندگان اصلی که در اواخر موضوع قرار دادند را بررسی کنید. آیا جواب آنها به طور سازندهای خلاصه است و با لحن مودبانهای تصمیم میگیرند؟ اگر چیزهای بیادبانهای میبینید، اغلب به این خاطر است که به جای توسعه، انرژی منفی میدهند — @kfogel, Producing OSS چگونه درخواست مشارکت را ارسال کنیم زمانی که پروژهی مورد علاقهتان را پیدا کردید، آمادهی مشارکت در آن میشوید و در نهایت باید راهی برای ارسال مشارکت خود به آن پیدا کنید. ارتباط موثر خواه مشارکتکنندهی یکباره باشید، یا سعی داشته باشید در یک انجمن عضو شوید، کار کردن با دیگران میتواند یکی از مهمترین مهارتهایی باشد که در مشارکت در پروژهی متن باز میتوانید آن را توسعه و بهبود دهید. من به عنوان یک مشارکتکنندهی جدید به سرعت متوجه شدم که اگر میخواهم مسائل مرتبط با پروژه متن باز را برطرف کنم، باید سوال بپرسم. کد را سرسری مطالعه کردم، به خود آمدم و خواستم من را بیشتر راهنمایی کنند. در نتیجه، بعد از دریافت تمام جزئیاتی که نیاز داشتم، توانستم مسائل پروژه را برطرف کنم — @shubheksha, A Beginner’s Very Bumpy Journey Through The World of Open Source قبل از درخواست ادغام یا باز کردن issue در بخش گزارش مسئله یا پرسیدن سوال در چت، نکتههای زیر را در نظر داشته باشید تا به شما کمک کند تا ایدههایتان کارآمد و موثرتر باشد. ارائهی زمینه: به دیگران کمک کنید تا سرعت خود را افزایش دهند. اگر خطایی پیدا کردید و در حال برطرف کردن آن هستید، به دیگران توضیح دهید که سعی دارید چه کاری انجام میدهید و چگونه آن مشکل را حل میکنید. اگر ایدهی جدیدی هم پیشنهاد میدهید، نه تنها برای خود، بلکه برای دیگران توضیح دهید که چرا فکر میکنید این ایدهی شما میتواند برای پروژه مفید باشد. 😇 “زمانی که Y را انجام میدهم، X اتفاق نمیافتد” 😢 “X به مشکل برخورد کرده است! لطفا برطرفش کنید.” تکالیفتان را از قبل انجام دهید. اگر چیزی نمیدانید مشکلی نیست، اما باید نشان دهید که تلاشتان را میکنید. قبل از اینکه از دیگران کمک بخواهید، مطمئن شوید که فایل README ، اسناد، مسائل حل شده یا حل نشده، لیست پست پروژه را خواندهاید، یا در اینترنت به دنبال جوابتان گشتهاید. وقتی تلاشتان برای یادگیری را نشان میدهید، مورد توجه تحسین دیگران قرار میگیرید 😇 “مطمئن نیستم چگونه X را اجرا کنم. برای پیدا کردن جواب، فایلها را بررسی کردم و هیچ جوابی نگرفتم.” 😢 “چگونه مسئله X را برطرف کنم؟” درخواستها را مختصر و مفید مطرح کنید هر مشارکتی مانند ارسال یک ایمیل، بدون در نظر گرفتن ساده یا مفید بودنش، به توجهی دیگران نیاز دارد. معمولاً درخواستها و سوالات اکثر پروژهها از افرادی که میخواهند به آنها جواب بدهند بیشتر است. بنابراین، درخواستها باید مختصر باشد. با کوتاه بودن درخواستها به افراد شانس بیشتری میدهید تا فرصت کمک کردن به شما را پیدا کنند. 😇 “تمایل دارم یک فایل آموزشی API بنویسم” 😢 “زمانی که در بزرگراه در حال رانندگی کردن بودم، کنار یک پمپ بنزین توقف کردم و ایدهی شگفتانگیزی به ذهنم رسید که باید آن را عملی کنیم، اما قبل از توضیح، اجازه دهید ایدهام را به شما نشان بدهم …“ تمام ارتباطات و تعاملات را به صورت عمومی نگهدارید. هرچند وسوسهکننده است، اما به طور خصوصی با مسئولنگهداری پروژه تماس نگیرید مگر اینکه لازم باشد اطلاعات حساس مانند مسائل امنیتی یا نقض رفتار جدیدی را رد و بدل کنید. زمانی که مکالمهی شما عمومی شود، افراد بیشتری از تبادل این ارتباطات یاد میگیرند و بهره میگیرند. بحث و گفتگوها میتواند خودبه خود کمکرسان باشد. 😇 (در کامنت) «@-مسئولنگهداری: سلام! چگونه درخواست ادغام را پیش ببریم؟”_ 😢 (در ایمیل) «سلام، ببخشید از طریق ایمیل مزاحم میشم، اما نمیدانم که میتوانید درخواست ادغام من را بررسی کنید.»_ سوال کردن عیب نیست (اما صبور باشید!). هرکسی در ابتدای کار در پروژه تازهوارد بوده است. حتی مشارکتکنندههای باتجربه زمانی که به پروژهی جدیدی مراجعه میکنند، باید سرعت خود را افزایش دهند. با این حساب، حتی مسئولنگهدارهای طولانی مدت هم همیشه با تمام بخشهای یک پروژه آشنا نیستند. بنابراین، سعی کنید صبور باشید تا فرصت نشان دادن آن را به شما بدهند. 😇 “بابت بررسی کردن این خطا ممنونم. پیشنهادهای شما را دنبال میکنم. این خروجی کار است” 😢 “چرا مشکل من را نمیتوانید حل کنید؟ این پروژه مگر پروژهی شما نیست؟” به تصمیمات انجمن احترام بگذارید. ایدههای شما ممکن است با اولویتها و دید انجمن متفاوت باشد. آنها یا میتوانند به ایدههای شما بازخورد بدهند یا آن را دنبال نکنند. درحالیکه باید بحث و گفتگو کنید و به دنبال مصالحه باشید، مسئولنگهداری باید با تصمیمات شما بیشتر از شما زندگی کند. اگر با مسیر آنها مخالف هستید، همیشه میتوانید روی کار خود تمرکز کنید و پروژهی خودتان را شروع کنید. 😇 “ناامید شدم که نمیتوانید پروندهی من را پشتیبانی کنید، اما همانطور که توضیح دادید این مسئله تنها روی بخشی از کاربران تاثیر میگذارد. متوجه هستم چرا. بابت شنیدن پیامم ممنون هستم” 😢 “چرا مورد من را پشتیبانی نمیکنید؟ این کار شما غیرقابل قبول است!” فراتر از همه اینها. مشارکتکنندههای سراسر دنیا پروژههای متن باز را میسازند. متنهای پروژهها میتواند با زبانها، فرهنگها، جغرافیاها و مناطق زمانی زیادی باشد. مدل ارتباط نوشتاری رساندن لحن و حالت مشارکتکنندههای یک پروژه را مشکل میکند. اما نیت خیر تمام این گفتگوها را در نظر داشته باشید. خوب است که ایدهی خود را مودبانه منتقل کنید، متن و محتوای بیشتری درخواست کنید، یا موقعیتتان را روشنتر کنید. فقط سعی کنید اینترنت را از زمانی که وارد شدید، را جای بهتری کرده باشید Gathering context قبل از اینکه کاری انجام دهید، به سرعت بررسی کنید و مطمئن شوید که ایدهی شما در هیج جای مورد بحث قرار نگرفته باشد. فایل README ، مسائل حلشده یا حلنشده، لیست پست و گفتگوهای Stack را به طور سرسری مطالعه کنید. لازم نیست ساعتها صرف خواندن آنها کنید، اما جستجوی سریع دربارهی کلمات کلیدی میتواند تا حد زیادی به شما کمک کند اگر ایدهی شما در جای دیگری مطرح نشده بود، میتوانید آن را بیان کنید. اگر پروژه در GitHub باشد، با باز کردن Issue یا درخواست ادغام Pull Request احتمالاً میتوانید مکالمه داشته باشید: Issues مانند شروع یک مکالمه یا گفتگو است Pull Requests برای کار روی راهحل است سایر راه های ارتباطی راههای ارتباطی مانند شفافسازی، نحوهی پرسیدن سوال (How-to question) ، پرسیدن سوال در Stack ، IRC ، Slack یا دیگر کانالهای چت است، البته اگر یک پروژه چنین راههای ارتباطی را باز گذاشته باشد. قبل از باز کردن issue یا درخواست ادغام، اسناد مشارکت پروژه را بررسی کنید که معمولاً در فایلهایی به نام CONTRIBUTING یا README آورده شدند تا چیزهای خاصی که دنبالش هستید را مطالعه کنید. به عنوان مثال، آنها ممکن است از شما درخواست کنند الگوها را پیروی کنید یا به این نیاز داشته باشند که از این تستها استفاده کنند. اگر در یک پروژه مشارکت عمیق و اساسی داشته باشید، قبل از مشارکت در پروژه، یک issue باز کنید و سوال کنید. این کار مفید است و باعث میشود پروژهی شما مدتی مشاهده شود. (در سایت GitHub میتوانید روی «Watch» کلیک کنید تا از تمام مکالمات مطلع شوید)، و قبل از انجام دادم کار که ممکن است پذیرفته نشود، اعضای انجمن را بشناسید. با فعالیت در پروژههای GitHub و مطالعهی تمام issue و درخواستهای ادغام میتوانید چیزهای زیادی یاد بگیرید. — @gaearon on joining projects باز کردن issue یا طرح سوال و گفتگو در موقعیتهای زیر معمولاً باید یک issue باز کنید: جهت گزارش خطایی که خودتان نمیتوانید آن را حل کنید دربارهی موضوعات یا ایدهی سطح بالا بحث کنید (به عنوان مثال، دربارهی جامعه، دیدگاه یا سیاستها) ویژگی جدید یا ایدهی جدیدی برای پروژه پیشنهاد دهید نکاتی برای برقراری ارتباط با مشکلات issue : اگر با مسئلهی بازی روبهرو شدید که میخواهید آن را برطرف کنید ، کامنت کردن برای یک مسئله به افراد اجازه میدهد بدانند که شما این مسئله را باز کردید. به این ترتیب، افراد احتمالاً کمتر با مشکلات مشابهی شما برخورد میکنند اگر یک issue مدتی پیش باز بوده است ، احتمال دارد جای دیگر به آن جواب داده شده باشد، یا قبلا حل شده است. بنابراین، قبل از شروع کار میتوانید برای تایید حل شدن یا حل نشدن آن درخوست کامنت بدهید. اگر یک issue باز کردید ، اما جواب آن را بعدها متوجه شدید، روی issue کامنت بگذارید تا مردم متوجه شوند، سپس issue را ببندید. حتی با نوشتن اسناد میتواند سهمی در مشارکت پروژه داشته باشید. ارسال Pull request (درخواست ادغام) شما معمولاً در موقیعتهای زیر باید درخواست ادغام باز کنید: ارائه اصلاحات ناچیز (به عنوان نمونه، غلطهای املائی، لینکهای خراب یا خطاهای مشهود) کار کردن روی مشارکتی که قبلا درخواست شده یا دربارهی آن بحث و گفتگو شده باشد درخواست ادغام لزوماً به معنای پایان کار نیست. معمولاً بهتر است درخواست ادغام را قبلا باز کنید تا دیگران بتوانند آن را مشاهده و بازخوردهای خود را برای پیشرفت شما ارسال کنند. فقط آن را به «WIP» (کار در حال انجام) در کادر عنوان نشانهگذاری کنید. شما بعدها میتوانید کامیتهای بیشتری اضافه کنید. اگر پروژه در GitHub باشد، با روشهای زیر میتوانید درخواست ادغام ارسال کنید: Fork the repository و یک نسخه برای خودتان کپی کنید. نسخه محلی خود را به مخزن بالادستی متصل کنید. هر از چندگاهی با دستور Pull آخرین نسخه تغییرات در مخزن اصلی را دریافت کنید تا پیش از اینکه تعارضی ما بین نسخه محلی و مخزن ایجاد شد بتوانید با مشکلات احتمالی کمتری تغییرات خود را به سمت مخزن اصلی ارسال کنید. برای کسب اطلاعات بیشتر اینجا را مرور کنید ایجاد یک شاخه برای اعمال ویرایش ها. در حین ارسال ها به مسائل (issue) مرتبط ارجاع دهید یا در کامنت مربوط به تغییرات جدید به مستندات مربوطه اشاره کنید.(مثال: این تغییر مشکل مطرح شده در مسئله شماره 37 را برطرف میکند.) اگر تغییرات شما حاوی تفاوتهای HTML/CSS باشد، تصاویر مربوط به قبل و بعد آن را اضافه کنید . تصاویر را وارد بدنهی درخواست ادغام کنید و رها کنید. تغییراتتان را تست کنید! تغییرات خود را در برابر تستهای موجود اجرا کنید و در صورت لزوم تغییرات جدیدی خلق کنید. اگر حتی تستهایی تعریف نشده بود، مطمئن شوید تغییراتتان پروژهی موجود شما را خراب نکند. با تمام تواناییتان الگوها را رعایت کرده و مطابق سبک پروژه مشارکت کنید . این توانایی میتواند به معنای استفاده از تورفتگیها، نقطه ویرگول (semi-colons) ، یا کامنتهای متفاوتی باشد که شما در مخزنتان خودتان دارید. این کار ادغام مسئولنگهداری را ساده میکند، دیگران هم متوجه آن میشوند و میتوانند آن را برای زمانهای آتی حفظ کنند. اگر این اولین درخواست ادغام شماست، فیلم آموزشی Make a Pull Request که @kentcdodds آن را خلق کرده، بررسی کنید. شما همچنین میتوانید از Make a Pull Request که توسط @Roshanjossey ایجاد شده به عنوان یک محزن تمرینی برای اولین تجربه خود استفاده کنید. بعد از ارسال درخواست مشارکت چه اتفاقی میافتد شما درخواستتان را ارسال کردید! شروع مشارکتتان در یک پروژهی متن باز را تبریک میگوییم. امیدواریم این اولین قدمتان باشد. بعد از ارسال درخواست مشارکتتان، یکی از اتفاقات زیر رخ میدهد: 😭 جوابی دریافت نمیکنید. امیدواریم قبل از ارسال درخواست مشارکت، چک لیست فعالیتهای پروژه را برررسی کرده باشید. هرچند، حتی در پروژهی فعال هم این احتمال وجود دارد که به درخواست مشارکت شما پاسخ ندهند. اگر بیش از یک هفته جوابی برایتان ارسال نشد، به طور مودبانه میتوانید درخواست جواب دهید و از کسی بخواهید درخواست شما را بررسی کند. اگر نام کسی که میخواهید درخواست شما را بررسی کند میدانید، می توانید به اون اشاره (منشن: با گذاشتن علامت @ در ابتدای نام کاربری) کنید. به صورت خصوصی با آن شخص تماس نگیرید . به یاد داشته باشید ارتباط عمومی برای پروژهها بسیار حیاتی است. اگر به طور مودبانه درخواستهایتان را فرستاده باشید اما هنوز هیچکس پاسخگو نیست، احتمالاً هیچکس هیچوقت پاسخ شما را نخواهد داد. میدانیم که حس خوبی ندارد، اما اجازه ندهید این موضوع شما را دلسرد کند چون این اتفاق ممکن است برای همه رخ دهد! برای برطرف کردن این مشکل دلایل زیادی وجود دارد که به شما میگوید چرا پاسخ درخواستتان داده نمیشود؛ دلایلی مانند شرایط شخصی که ممکن است از کنترل خارج شود. شما میتواند پروژهی دیگر یا راهی برای مشارکت پیدا کنید. قبل از اینکه اعضای یک انجمن متعهد یا پاسخگو باشند، زمان زیادی را صرف ارسال درخواست مشارکتتان نکنید. 🚧 یک نفر برای تغییر درخواستتان به شما پیام میدهد. مرسوم است کسی بخواهید درخواست مشارکت خود را تغییر دهید، این درخواست تغییر میتواند در بازخورد ایده یا در تغییرات کد شما باشد. اگر کسی درخواست تغییر برایتان ارسال کرد، پاسخگو باشید، چون آنها برای بررسی درخواست مشارکت شما زمان گذاشتند. باز گذاشتن PR (درخواست ادغام) و نادیده گرفتن آن صورت خوبی ندارد. اگر نمیدانید چگونه روی درخواستتان آن تغییرات را اعمال کنید، مشکلات را جستجو کنید و در صورت نیاز از کسی کمک بخواهید. اگر برای برطرف کردن مسائل پروژه دیگر زمان کافی ندارید (به عنوان نمونه، اگر مکالمه | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/skan-ai-skan-cpx-skan-cognitive-process-discovery-and-operational-intelligence-platform/?trk=products_seo_search | Skan AI Process Intelligence Platform | LinkedIn Skip to main content LinkedIn Skan AI in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Skan AI Process Intelligence Platform Business Process Management Software by Skan AI See who's skilled in this Add as skill Request demo Report this product About See how work really happens across your entire organization. Our platform captures complete end-to-end processes across every application and user, creating accurate digital twins that reveal inefficiencies others miss. Move from guesswork to certainty with continuous monitoring that spots issues before they become costly and validates improvements after implementation. Traditional process discovery tools leave you blind. Process mining only sees what's logged in your systems—missing the human work that makes up most of your operations. Task mining captures individual actions but can't stitch them into complete processes. Skan's Process Intelligence observes everything: every application including mainframes and VDI, every click, every handoff, every variation. We deploy in weeks, not months, with zero system integrations required. You get the full picture of how work flows across any operation. This product is intended for Operations Manager Chief Financial Officer Chief Operating Officer Process Manager Business Process Manager Media Products media viewer No more previous content What is Skan? With Skan’s process intelligence technology, you can now continuously understand how real work is being done. We can help you unlock your business’ potential to be greater at driving operational excellence, business transformation, and continuous improvement. No more next content Featured customers of Skan AI Process Intelligence Platform Drax Group Utilities 56,486 followers Cisive Human Resources Services 29,528 followers Unum Insurance 96,511 followers Dell Technologies Computer Hardware Manufacturing 5,431,605 followers Protective Life Insurance 38,562 followers Mitie Facilities Services 213,757 followers Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#the-rust-programming-language | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
http://git-scm.com/cheat-sheet#push-your-changes | Git Cheat Sheet About Trademark Learn Book Cheat Sheet Videos External Links Tools Command Line GUIs Hosting Reference Install Community Table of Contents Getting Started Prepare to Commit Make Commits Move Between Branches Diff Staged/Unstaged Changes Diff Commits Ways to refer to a commit Discard Your Changes Edit History Code Archaeology Combine Diverged Branches Restore an Old File Add a Remote Push Your Changes Pull Changes Configure Git Important Files The entire Pro Git book written by Scott Chacon and Ben Straub is available to read online for free . Dead tree versions are available on Amazon.com . Git Cheat Sheet Getting Started Start a new repo: git init Clone an existing repo: git clone <url> Prepare to Commit Add untracked file or unstaged changes: git add <file> Add all untracked files and unstaged changes: git add . Choose which parts of a file to stage: git add -p Move file: git mv <old> <new> Delete file: git rm <file> Tell Git to forget about a file without deleting it: git rm --cached <file> Unstage one file: git reset <file> Unstage everything: git reset Check what you added: git status Make Commits Make a commit (and open text editor to write message): git commit Make a commit: git commit -m 'message' Commit all unstaged changes: git commit -am 'message' Move Between Branches Switch branches: git switch <name> OR git checkout <name> Create a branch: git switch -c <name> OR git checkout -b <name> List branches: git branch List branches by most recently committed to: git branch --sort=-committerdate Delete a branch: git branch -d <name> Force delete a branch: git branch -D <name> Diff Staged/Unstaged Changes Diff all staged and unstaged changes: git diff HEAD Diff just staged changes: git diff --staged Diff just unstaged changes: git diff Diff Commits Show diff between a commit and its parent: git show <commit> Diff two commits: git diff <commit> <commit> Diff one file since a commit: git diff <commit> <file> Show a summary of a diff: git diff <commit> --stat git show <commit> --stat Ways to refer to a commit Every time we say <commit> , you can use any of these: a branch main a tag v0.1 a commit ID 3e887ab a remote branch origin/main current commit HEAD 3 commits ago HEAD^^^ or HEAD~3 Discard Your Changes Delete unstaged changes to one file: git restore <file> OR git checkout <file> Delete all staged and unstaged changes to one file: git restore --staged --worktree <file> OR git checkout HEAD <file> Delete all staged and unstaged changes: git reset --hard Delete untracked files: git clean 'Stash' all staged and unstaged changes: git stash Edit History "Undo" the most recent commit (keep your working directory the same): git reset HEAD^ Squash the last 5 commits into one: git rebase -i HEAD~6 Then change "pick" to "fixup" for any commit you want to combine with the previous one Undo a failed rebase: git reflog BRANCHNAME Then manually find the right commit ID in the reflog, then run: git reset --hard <commit> Change a commit message (or add a file you forgot): git commit --amend Code Archaeology Look at a branch's history: git log main git log --graph main git log --oneline Show every commit that modified a file: git log <file> Show every commit that modified a file, including before it was renamed: git log --follow <file> Find every commit that added or removed some text: git log -G banana Show who last changed each line of a file: git blame <file> Combine Diverged Branches Combine with rebase: git switch banana git rebase main Before: After: Combine with merge: git switch main git merge banana Before: After: Combine with squash merge: git switch main git merge --squash banana git commit Before: After: Bring a branch up to date with another branch (aka "fast-forward merge"): git switch main git merge banana Before: After: Copy one commit onto the current branch: git cherry-pick <commit> Before: After: Restore an Old File Get the version of a file from another commit: git checkout <commit> <file> OR git restore <file> --source <commit> Add a Remote git remote add <name> <url> Push Your Changes Push the main branch to the remote origin : git push origin main Push the current branch to its remote "tracking branch": git push Push a branch that you've never pushed before: git push -u origin <name> Force push: git push --force-with-lease Push tags: git push --tags Pull Changes Fetch changes (but don't change any of your local branches): git fetch origin main Fetch changes and then rebase your current branch: git pull --rebase Fetch changes and then merge them into your current branch: git pull origin main OR git pull Configure Git Set a config option: git config user.name 'Your Name' Set option globally: git config --global ... Add an alias: git config alias.st status See all possible config options: man git-config Important Files Local git config: .git/config Global git config: ~/.gitconfig List of files to ignore: .gitignore About this site Patches, suggestions, and comments are welcome. Git is a member of Software Freedom Conservancy | 2026-01-13T09:29:16 |
https://docs.softwareheritage.org/index.html | Welcome to Software Heritage documentation — Software Heritage documentation Skip to main content Back to top Ctrl + K Development API reference Usage Resources Infrastructure More About GitLab PyPI System Status Software Heritage Homepage Development API reference Usage Resources Infrastructure About GitLab PyPI System Status Software Heritage Homepage Welcome to Software Heritage documentation # Basics Learn about our mission and our source code archive. Find out about how to make your first steps with the archive. Discover Software Heritage Discover Software Heritage Preserve All the ways that source code may be added or updated in the archive. Archive source code Archive and reference source code Browse Our vast archive can be searched and accessed in multiple ways. Use it to reference unambiguously any part of a source code to your peers: fragment of code, directory, release, etc. Learn how to search the archive Search, browse and reference Learn and share Explore our full collection of training content, trainer resources, and organizational strategy documents. Discover the ambassadors programme. Train yourself and learn Learn and share Interface Develop or research using Software Heritage. Browse, access or import source code programmatically. Use Software Heritage in your applications Use in your applications Develop Enhance our collection, preservation, and querying processes. Improve the universal archive of source code Improve the universal archive Discover Software Heritage # Learn about our mission and our source code archive. Find out about how to make your first steps with the archive. Why an universal software archive? # A video to get to know Software Heritage Our mission Our approach The content of the archive at a glance Software Heritage in practice # Take a guided tour of the archive key features Overview of the main features Access and reuse the source code Good practices for archiving and referencing your code Get a permanent identifier for your source code General FAQ Glossary Archive and reference source code # There are multiple ways to add or update source code in Software Heritage archive. Some of them are automated: our tools crawl multiple software development plateforms to archive as many open projects as possible. Others require manual procedures. Before anything… # Good practices for archiving and referencing your code Save a code repository # “Ready to go” options to save your code : Seamlessly check if a repository that you are browsing is archived and up to date using our Software Heritage browser extensions Submit a save request on the Software Heritage interface Automate the archival: Trigger a GitHub action that saves the GitHub repository Trigger archival of a repository automatically : Bitbucket endpoint, GitHub endpoint, GitLab endpoint Deposit artefacts and/or metadata # The deposit service allows a trusted partner to submit software source archives and its associated metadata to the Software Heritage archive. Metadata can be also submitted referencing a repository url (origin). Discover the deposit service Save multiple projects at a time, save a forge # Save a forge in 2 steps : Create an account Submit a request of archival for to save a complete forge Technical insight on the “Add forge now” process Save legacy source code # Recovering and curating landmark legacy source code : how to save legacy code Search, browse and reference # Search and access the archive, or use it to reference unambiguously any part of a source code. Take the guided tour of the archive web interface Good practices for archiving and referencing your code Make your code identifiable : get a PID for your source code Choosing what type of Software Hash Identifier (SWHID) to use Navigating through Software Heritage: behind the scenes Need help? Want to make a proposal? Ask the community using the users mailing-list Learn and share # Developers, software engineers, researchers, academic librarians, metadata curators, and software archivists: get trained on Software Heritage, or find the resources you need to train others. Software Heritage advocates will also find documentation for a deeper understanding of the overall strategy. Any feedback, any question? community-care @ softwareheritage . org Learning resources # Find out learning resources for end-users and trainers, presentations, strategic documents, etc. Ambassador program # Become an ambassador Ambassadors mailing list Resources related to the ambassadors’ program Use in your applications # Interact with our source code archive from your applications or research projects. Browse API # Terms of use for Software Heritage API Web API . Access the API overview or discover the full endpoints index Data model and identifiers # Our data model Software Hash IDentifiers (SWHID) specifications Compute a SWHID locally using the swh identify command-line tool. Deposit API # Import source code programmatically Improve the universal archive # There are many ways to help Software Heritage. However small or large, contributions are welcome and very much appreciated. Our roadmap Developer documentation . Where you will find developer-oriented documentation to understand the SWH environment. Get started Contributing development skills: Software architecture overview Developers portal Development mailing-list . Join the community Development FAQ Contributing resources and infrastructure: Mirror operations Table of contents # Development Getting started Contributing Architecture Data Model and Specifications Tutorials Roadmap System Administration Components Dependencies Archive API reference swh.alter swh.auth swh.coarnotify swh.core swh.counters swh.dataportal swh.datasets swh.deposit swh.digestmap swh.export swh.fuse swh.graph swh.graph.libs Software Heritage GraphQL API Design swh.indexer swh.journal swh.lister swh.loader swh.model swh.objstorage swh.objstorage.replayer Software Heritage - Provenance Description swh.scanner swh.scheduler swh.scrubber swh.search swh.shard swh.storage swh.vault swh.web swh.web.client swh.webhooks Usage Frequently Asked Questions Software Origins Software Heritage listers Software Heritage loaders Software Heritage Webhooks Using Software Heritage data Software Heritage Deposit Service Software Heritage COAR Notify Inbox Software Heritage Datasets Resources Ambassadors’ materials Learning resources Presentations Data and code Documents Tutorials Infrastructure Getting started Puppet Network architecture Server Architecture (Physical/Virtual) Software Architecture Data silos SWH Software Deployment User management Life-cycle management Mirror Operations Support services About How to contribute How to build the doc Cleaning up Publishing the doc Building standalone package documentation next Development so the DOM is not blocked --> © Copyright 2015-2025 The Software Heritage developers. Created using Sphinx 7.4.7. Built with the PyData Sphinx Theme 0.16.1. | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=iyg4ytkAAAAJ&hl=ko&oe=ASCII | Jinyuan Jia - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 전체 2021년 이후 서지정보 8268 7913 h-index 38 38 i10-index 58 58 0 3100 1550 775 2325 2018 2019 2020 2021 2022 2023 2024 2025 2026 34 59 235 502 857 1340 2118 3012 80 공개 액세스 모두 보기 모두 보기 자료 41개 자료 0개 공개 비공개 재정 지원 요구사항 기준 팔로우 Jinyuan Jia Assistant Professor, Penn State psu.edu의 이메일 확인됨 - 홈페이지 AI Security 학술자료 인용 공개 액세스 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Local Model Poisoning Attacks to Byzantine-Robust Federated Learning M Fang, X Cao, J Jia, NZ Gong USENIX Security Symposium , 2020 1923 2020 MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples J Jia, A Salem, M Backes, Y Zhang, NZ Gong ACM Conference on Computer and Communications Security (CCS) , 2019 551 2019 FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients Z Zhang, X Cao, J Jia, NZ Gong ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) , 2022 407 2022 Formalizing and Benchmarking Prompt Injection Attacks and Defenses Y Liu, Y Jia, R Geng, J Jia, NZ Gong USENIX Security Symposium , 2024 333 2024 Backdoor attacks to graph neural networks Z Zhang, J Jia, B Wang, NZ Gong ACM Symposium on Access Control Models and Technologies (SACMAT) , 2021 320 2021 {PoisonedRAG}: Knowledge Corruption Attacks to {Retrieval-Augmented} Generation of Large Language Models W Zou, R Geng, B Wang, J Jia USENIX Security Symposium, 3827-3844 , 2025 291 2025 BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning J Jia, Y Liu, NZ Gong IEEE Symposium on Security and Privacy (IEEE S&P) , 2022 272 2022 Stealing Links from Graph Neural Networks X He, J Jia, M Backes, NZ Gong, Y Zhang USENIX Security Symposium , 2021 257 2021 AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning J Jia, NZ Gong USENIX Security Symposium , 2018 253 2018 IPGuard: Protecting the Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary X Cao, J Jia, NZ Gong ACM ASIA Conference on Computer and Communications Security (ASIACCS) , 2021 233 2021 SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding Z Xu, F Jiang, L Niu, J Jia, BY Lin, R Poovendran Annual Meeting of the Association for Computational Linguistics (ACL) , 2024 216 2024 Provably Secure Federated Learning against Malicious Clients X Cao, J Jia, NZ Gong AAAI Conference on Artificial Intelligence (AAAI) , 2021 197 2021 Random walk based fake account detection in online social networks J Jia, B Wang, NZ Gong IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) , 2017 175 2017 Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks J Jia, X Cao, NZ Gong AAAI Conference on Artificial Intelligence (AAAI) , 2021 160 2021 FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information X Cao, J Jia, Z Zhang, NZ Gong IEEE Symposium on Security and Privacy (IEEE S&P) , 2023 148 2023 Data Poisoning Attacks to Local Differential Privacy Protocols X Cao, J Jia, NZ Gong USENIX Security Symposium , 2021 139 2021 On Certifying Robustness against Backdoor Attacks via Randomized Smoothing B Wang, X Cao, J Jia, NZ Gong CVPR 2020 Workshop on Adversarial Machine Learning in Computer Vision , 2020 138 2020 EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning H Liu, J Jia, W Qu, NZ Gong ACM Conference on Computer and Communications Security (CCS) , 2021 130 2021 AttriInfer: Inferring user attributes in online social networks using markov random fields J Jia, B Wang, L Zhang, NZ Gong Proceedings of the WWW, 1561-1569 , 2017 128 2017 Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing J Jia, X Cao, B Wang, NZ Gong International Conference on Learning Representations (ICLR) , 2020 120 2020 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fdataport-a%25C3%25B6r-dworkflow%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/rsasecurity-rsa-governance-lifecycle/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click#main-content | RSA Governance &amp; Lifecycle | LinkedIn Skip to main content LinkedIn RSA Security in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in RSA Governance & Lifecycle Identity & Access Management (IAM) Software by RSA Security See who's skilled in this Add as skill Learn more Report this product About RSA Governance & Lifecycle provides complete identity governance and administration (IGA) capabilities in cloud, hybrid, or on-premises deployments. The solution provides organizations with the resources they need to improve compliance, reduce risk, and optimize operations. RSA Governance & Lifecycle also provides a dynamic dashboarding feature that allows organizations to identify trends and uncover risks, and gamification to accelerate reviews and reduce audit cycles. Media Products media viewer No more previous content RSA and Sorenson Communications Sorenson Communications is one of the world’s leading language services providers and the world’s leading provider of communication tools for Deaf and hard-of-hearing people. Sorenson Communications IT Director of IT Security Steve Yeo and RSA Governance & Lifecycle Field CTO Chris Williams explain the challenges that Sorenson Communications faced when moving to a multicloud environment and why RSA Governance & Lifecycle was “pivotal” to ensuring its data, security, and mission. No more next content Similar products Crowd Crowd Identity & Access Management (IAM) Software Cloudflare Access Cloudflare Access Identity & Access Management (IAM) Software Saviynt Intelligence Saviynt Intelligence Identity & Access Management (IAM) Software Akamai Identity Cloud Akamai Identity Cloud Identity & Access Management (IAM) Software Veridian Veridian Identity & Access Management (IAM) Software Teleport Teleport Identity & Access Management (IAM) Software Sign in to see more Show more Show less RSA Security products ID Plus ID Plus Identity & Access Management (IAM) Software SecurID SecurID Multi-Factor Authentication (MFA) Software LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://huggingface.co/papers | Daily Papers - Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up new Get trending papers in your email inbox once a day! Get trending papers in your email inbox! Subscribe Daily Papers by AK and the research community Daily Weekly Monthly Jan 13 Submitted by Yu2020 118 Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning · 16 authors 1 3 Submitted by taesiri 100 BabyVision: Visual Reasoning Beyond Language · 29 authors 3 Submitted by reign12 55 PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning StepFun 1 Submitted by taesiri 23 X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests · 10 authors 15 Submitted by YerbaPage 22 GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts Shanghai Jiao Tong University 5 2 Submitted by yfdeng10 20 MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head DAGroup-PKU 34 1 Submitted by Seongyun 20 Lost in the Noise: How Reasoning Models Fail with Contextual Distractors KAIST AI 1 Submitted by heroding77 19 OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent university of science and technology of china 14 1 Submitted by zhongzero 16 Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models · 9 authors 12 1 Submitted by zisuh 14 Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction · 11 authors 2 Submitted by Lemoncoke 13 MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era · 18 authors 1 Submitted by KaiiWuu1993 13 Boosting Latent Diffusion Models via Disentangled Representation Alignment Kolors Team, Kuaishou Technology 1 Submitted by yangzhou99 13 DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving University of Toronto 5 1 Submitted by zhangboguodong 12 ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration Renmin University of China 1 Submitted by Dasool 12 What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models HAE-RAE 10 1 Submitted by lixiaoxi45 8 TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning · 8 authors 1 Submitted by taesiri 5 Dr. Zero: Self-Evolving Search Agents without Training Data · 8 authors 4 1 Submitted by zsqzz 4 OpenTinker: Separating Concerns in Agentic Reinforcement Learning · 2 authors 563 1 Submitted by deqing 3 Are LLM Decisions Faithful to Verbal Confidence? University of Southern California 1 Submitted by crazyofapple 3 Structured Episodic Event Memory Harbin Institute of Technology 1 Submitted by imranraad 2 "TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt · 2 authors 1 Submitted by KomeijiForce 2 Codified Foreshadowing-Payoff Text Generation · 5 authors 1 Submitted by Haon-Chen 2 e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings · 5 authors 1 Submitted by taesiri 1 ShowUI-Aloha: Human-Taught GUI Agent · 8 authors Submitted by taesiri 1 SketchJudge: A Diagnostic Benchmark for Grading Hand-drawn Diagrams with Multimodal Large Language Models · 7 authors Submitted by Akhil-Theerthala 1 FinForge: Semi-Synthetic Financial Benchmark Generation Financial Services Innovation Lab, Georgia Tech 1 Submitted by SteveZeyuZhang - 3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence Peking University 0 1 Submitted by dlion168 - On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation · 8 authors 1 Previous System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
http://www.ifross.org/?q=node/1021 | Lizenz-Center | ifrOSS Institut für Rechtsfragen der Freien und Open Source Software Aktuelles Publikationen Rechtspolitik Lizenzen GPL Urteile Creative Commons FAQ Institut --> --> You are here Startseite › Lizenz-Center ifrOSS News Embedded-Linux-Woche mit technischen und rechtlichen Themen vom 21.-25.10.2024 in Würzburg Workshop „Rechtsfragen bei OSS“ von Till Kreutzer an der Universität Münster am 29.06.2023 Gespräch von Nils Pooker und Till Jaeger zum Thema " Wie KI Kunst und Urheberrecht verändert " bei der re:publica 2023 am 07.06.2023 Suchen Suchen Anmeldung Benutzername * Passwort * Neues Passwort anfordern Sprachen English Deutsch --> Lizenz-Center Im Lizenzcenter des ifrOSS werden die Lizenzen für Freie Software, Open Source, Open Content, Open Data und Open Source Hardware gesammelt und verschiedenen Lizenztypen zugeordnet. Damit wird eine einfache Auffindbarkeit und Charakterisierung ermöglicht. https://ifross.github.io/ifrOSS/Pages/licence_center/de English Sprache Deutsch Nachrichten der Woche Derzeit sind keine aktuellen Nachrichten der Woche verfügbar. Ältere Nachrichten im Archiv . Nachrichtenarchiv 2025 (1) 2024 (1) 2023 (2) 2022 (2) 2021 (4) 2020 (8) 2019 (3) 2018 (7) 2017 (11) Login Kontakt Impressum Datenschutz | 2026-01-13T09:29:16 |
https://pt.linkedin.com/company/cloudflare | Cloudflare | LinkedIn Pular para conteúdo principal LinkedIn Artigos Pessoas Learning Vagas Jogos Entrar Cadastre-se agora Cloudflare Segurança de redes e computadores San Francisco, California 1.123.490 seguidores Na Cloudflare, temos objetivos ambiciosos: ajudar na construção de uma Internet melhor. Visualizar vagas Seguir Visualizar todos os 6.532 funcionários Denunciar esta empresa Visão geral Vagas Dia a dia Sobre nós Cloudflare, Inc. (NYSE: NET) is the leading connectivity cloud company. It empowers organizations to make their employees, applications and networks faster and more secure everywhere, while reducing complexity and cost. Cloudflare’s connectivity cloud delivers the most full-featured, unified platform of cloud-native products and developer tools, so any organization can gain the control they need to work, develop, and accelerate their business. Powered by one of the world’s largest and most interconnected networks, Cloudflare blocks billions of threats online for its customers every day. It is trusted by millions of organizations – from the largest brands to entrepreneurs and small businesses to nonprofits, humanitarian groups, and governments across the globe. Site https://www.cloudflare.com Link externo para Cloudflare Setor Segurança de redes e computadores Tamanho da empresa 1.001-5.000 funcionários Sede San Francisco, California Tipo Empresa de capital aberto Fundada em 2009 Especializações nginx, lua, go, web performance, web security, dns, network, noc, nocc, ddos, CDN, waf, zero trust security e developer tools Produtos Ver todos Não há mais conteúdo anterior Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Software de gerenciamento de identidade e acesso Cloudflare Access Software de gerenciamento de identidade e acesso Cloudflare CDN, Software de rede de entrega de conteúdo Cloudflare CDN Software de rede de entrega de conteúdo Cloudflare DDoS Protection, Software de proteção contra ataques DDoS Cloudflare DDoS Protection Software de proteção contra ataques DDoS Cloudflare DNS, Software de serviços de DNS gerenciados Cloudflare DNS Software de serviços de DNS gerenciados Cloudflare Load Balancing, Software de balanceamento de carga Cloudflare Load Balancing Software de balanceamento de carga Cloudflare Registrar, Software de serviços de DNS gerenciados Cloudflare Registrar Software de serviços de DNS gerenciados Cloudflare Spectrum, Software de proteção contra ataques DDoS Cloudflare Spectrum Software de proteção contra ataques DDoS Cloudflare SSL / TLS, Software de certificados SSL Cloudflare SSL / TLS Software de certificados SSL Cloudflare Stream, Software de transmissão ao vivo Cloudflare Stream Software de transmissão ao vivo Não há mais próximo conteúdo Produtos Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Software de gerenciamento de identidade e acesso Cloudflare Access Software de gerenciamento de identidade e acesso Cloudflare CDN, Software de rede de entrega de conteúdo Cloudflare CDN Software de rede de entrega de conteúdo Cloudflare DDoS Protection, Software de proteção contra ataques DDoS Cloudflare DDoS Protection Software de proteção contra ataques DDoS Cloudflare DNS, Software de serviços de DNS gerenciados Cloudflare DNS Software de serviços de DNS gerenciados Cloudflare Load Balancing, Software de balanceamento de carga Cloudflare Load Balancing Software de balanceamento de carga Cloudflare Registrar, Software de serviços de DNS gerenciados Cloudflare Registrar Software de serviços de DNS gerenciados Cloudflare Spectrum, Software de proteção contra ataques DDoS Cloudflare Spectrum Software de proteção contra ataques DDoS Cloudflare SSL / TLS, Software de certificados SSL Cloudflare SSL / TLS Software de certificados SSL Cloudflare Stream, Software de transmissão ao vivo Cloudflare Stream Software de transmissão ao vivo Cloudflare WAF, Firewalls de aplicativos web Cloudflare WAF Firewalls de aplicativos web Cloudflare Web Analytics, Software de análise digital Cloudflare Web Analytics Software de análise digital Cloudflare Workers, Software de virtualização de servidor Cloudflare Workers Software de virtualização de servidor Localidades Principal 101 Townsend St San Francisco, California 94107, US Como chegar Westminster Bridge Road 6th Floor, Riverside Building, County Hall London, England SE1 7PB, GB Como chegar 120 Robinson Road Frasers Tower #35-01 Singapore, Singapore 069547, SG Como chegar 405 Comal St Austin, Texas 78702, US Como chegar 10 Almaden Blvd Suite 200 San Jose, California 95113, US Como chegar Rosental 7 Munich, Bavaria 80331, DE Como chegar 301 N Neil St Suite 440 Champaign, Illinois 61820, US Como chegar 26-1 Sakuragaoka-cho Shibuya-ku, Level 15 Cerulean Tower Tokyo, 150-8512, JP Como chegar 16 South Guangshun Street Donghuang Building 17th Floor Beijing, Chaoyang District Beijing 100015, CN Como chegar Rue de la Loi 38 Brussels, Brussels Region 1000, BE Como chegar Praça Marquês de Pombal 14 7th floor Lisbon, 1250-162, PT Como chegar 6, Place de la Madeleine Mailing Address Only Paris, Île-de-France 75008, FR Como chegar 20 Martin Place Level 10 Sydney, NSW 2000, AU Como chegar 1401 K St NW Washington, District of Columbia 20005, US Como chegar Exibir mais localidades Exibir menos localidades Funcionários da Cloudflare Adam Edgmond Mark Nottingham Trevor Laughton Carl Ledbetter Ver todos os funcionários Atualizações Cloudflare 1.123.490 seguidores 8 h Denunciar esta publicação As we kick off the new year, we’re spotlighting Cloudflare leaders across multiple functions who will share their insights around technical trends and emerging threats in 2026. 🎥 Nan Hao Maguire, APAC & Japan Field CTO at Cloudflare, breaks down the urgent shifts in the threat landscape, from smarter AI-driven attacks to the emerging reality of quantum computing. Discover our technical predictions for 2026 in our Post Quantum Computing solution brief: https://cfl.re/3LyW1eC #Cybersecurity #QuantumComputing #AI #FutureofTech #Infrastructure #2026Trends …mais 25 2 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 14 h Denunciar esta publicação The margin is thinner than you think with modernizing applications. 📉 14% are behind schedule. 13% are ahead of schedule. This 1% difference can make or break your ability to innovate with AI. 🤖 Find out how in the 2026 Cloudflare App Innovation Report, dropping this Wednesday. 🚀 #AppInnovationReport #TechnologyInnovation #CyberSecurity 35 4 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 3 d Denunciar esta publicação 🤠 Dallas! The future of connectivity is coming to Frisco. Ready to connect with the leaders driving network modernization right here in Texas? Join us for Cloudflare Immerse Dallas on February 12th! We’re bringing together the region’s top security, IT, and digital leaders for an afternoon of deep dives into the Connectivity Cloud, Zero Trust, and AI application security. It’s more than just sessions—it’s your chance to network with peers and get your toughest questions answered at our "Ask the Cloudflare Experts" bar. 📍 Where: HALL Park Hotel, Frisco, TX 📅 When: Thursday, Feb 12, 2026 | 1:30 PM - 5:00 PM (Happy Hour to follow! 🍹) Spots are limited. Secure your seat today! 👇 https://lnkd.in/dEKuBqve #CloudflareImmerse #DallasTech #NetSec #FriscoTX #Networking #CyberSecurity #ConnectivityCloud 50 4 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 4 d Denunciar esta publicação What's your preferred method for knowledge sharing within a team (e.g., detailed READMEs, synchronous workshops, pairing)? #CloudflareChat 29 8 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 4 d Denunciar esta publicação We are thrilled to announce that Cloudflare has been recognized as the current Company to Beat in the December 2025 Gartner AI Vendor Race for Edge Distribution Platform AI! Discover the key findings of the report from our article 👇 Cloudflare named as the current Company to Beat in a Gartner® report for Edge Distribution Platform AI! Cloudflare no LinkedIn 657 11 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 5 d Editado Denunciar esta publicação Cloudflare is getting ready for ICE 2026 in Barcelona, taking place 19–21 January. We’ll be at Booth 4K30 sharing how Cloudflare for iGaming helps platforms deliver fast, secure, and reliable experiences for players around the world. If you’re attending, stop by to meet the team, explore our iGaming security solutions, and join us for a relaxed Happy Hour at the booth. If you pre-book a meeting with us, you’ll also be entered into a prize draw for a chance to win an exclusive FC Barcelona jersey on the first day of the event! Click here to book your meeting: https://lnkd.in/gSPe58K6 See you there! 33 Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 5 d Denunciar esta publicação Is your organization struggling to manage a sprawling attack surface across hybrid environments? Join Cloudflare and Werner Executive VP & CIO Daragh Mahon to hear directly from one of our customers on their successful real-world Zero Trust deployments. Learn more about priority use cases, common challenges, and architectural strategies. Register today! https://lnkd.in/db4Gb6Rk #ZeroTrust #Cybersecurity #Cloudflare #Webinar 41 2 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 5 d Denunciar esta publicação Defend against rising app-layer DDoS attacks 📱 In his latest article for theNET, Gregory Van den Top explains how DDoS attacks — often powered by AI — are a growing threat to applications. They can slow or completely crash software, bringing critical operations to a halt. The right strategic framework — focused on detecting, mitigating, and adapting — can help stop attacks and improve resilience: https://lnkd.in/dwuSqcm4 60 1 comentário Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 6 d Denunciar esta publicação A BGP route leak in Venezuela recently impacted internet connectivity. Our latest analysis breaks down how this happened and why it highlights the need for better routing security across the global Internet. https://cfl.re/4qEaNQ5 A closer look at a BGP anomaly in Venezuela blog.cloudflare.com 358 4 comentários Gostei Comentar Compartilhar Cloudflare 1.123.490 seguidores 6 d Denunciar esta publicação Cloudflare was proud to protect the Moldovan Central Election Commission during their elections. 🔗 Learn more about it on our blog: https://lnkd.in/gQ8P2NmB Anatolie Golovco 1 sem CloudFlare mentioned Moldova in their 2025 Annual Impact Report. As a personal tip to web studios that care about protecting their customers against DDoS attacks: take a look at CloudFlare Pages, CloudFlare R2, and Hugo CMS as alternatives to traditional hosting setups and content management systems. https://lnkd.in/dxgycsYm #CloudFlare 41 2 comentários Gostei Comentar Compartilhar Cadastre-se agora para ver o que você está perdendo Encontre pessoas conhecidas na Cloudflare Veja vagas recomendadas para você Visualize todas as atualizações, notícias e artigos Cadastre-se agora Páginas afiliadas Cloudflare for Public Sector Segurança de redes e computadores San Francisco, California Cloudflare Partner Network Segurança de redes e computadores Páginas semelhantes Akamai Technologies Tecnologia, Informação e Internet Cambridge, MA CrowdStrike Segurança de redes e computadores Palo Alto Networks Segurança de redes e computadores SANTA CLARA, California Atlassian Desenvolvimento de software Sydney, NSW Google Desenvolvimento de software Mountain View, CA Zscaler Segurança de redes e computadores San Jose, California Snowflake Desenvolvimento de software Microsoft Desenvolvimento de software Redmond, Washington Cisco Desenvolvimento de software San Jose, CA Databricks Desenvolvimento de software San Francisco, CA Exibir mais páginas semelhantes Exibir menos páginas semelhantes Visualizar vagas Vagas de Engenheiro 422 vagas Vagas de Executivo de contas 51 vagas Vagas de Analista 269 vagas Vagas de Diretor 280 vagas Vagas de Desenvolvedor 372 vagas Vagas de Gerente de vendas 116 vagas Vagas de Gerente de Marketing 141 vagas Vagas de Diretor de recursos humanos 27 vagas Vagas de Gerente de engenharia 139 vagas Vagas de Analista de dados 5.002 vagas Vagas de Desenvolvedor Python 972 vagas Vagas de Gerente de TI 57 vagas Vagas de Recrutador 27 vagas Vagas de Recursos humanos 913 vagas Vagas de Diretor de RH 43 vagas Vagas de CEO 399 vagas Vagas de Arquiteto 67 vagas Vagas de Engenheiro de dados 37 vagas Vagas de Redator 48 vagas Vagas de Comprador 64 vagas Exibir mais vagas como essa Exibir menos vagas como essa Mais pesquisas Mais pesquisas Vagas de Engenheiro Vagas de Diretor Vagas de Executivo de contas Vagas de Analista Vagas de Desenvolvedor Vagas de Gerente de vendas Vagas de Gerente de engenharia Vagas de Recrutador Vagas de Gerente de Marketing Vagas de Analista de dados Vagas de Desenvolvedor Python Vagas de Recursos humanos Vagas de Engenheiro de dados Vagas de CEO Vagas de Gerente de TI Vagas de Arquiteto Vagas de CTO Vagas de Marketing Vagas de Diretor de recursos humanos Vagas de Redator Vagas de Diretor de RH Vagas de Desenvolvedor Javascript Vagas de Analista de sistema Vagas de Gerente de eventos Vagas de Analista de riscos Vagas de Financeiro Vagas de Scrum master Vagas de Desenvolvedor .Net Vagas de Gerente comercial Vagas de Engenheiro de software Vagas de Arquiteto de software Vagas de Coordenador de marketing Vagas de Analista de marketing Vagas de Auditor Vagas de Engenheiro de qualidade Vagas de Desenvolvedor de aplicativos Vagas de Analista de investimento Vagas de Diretor de projetos Vagas de Analista financeiro Vagas de Diretor financeiro Vagas de Jornalista Vagas de Engenheiro industrial Vagas de Engenheiro de projetos Vagas de Assistente de marketing Vagas de Comprador Vagas de Assistente de pesquisa Vagas de Analista de vendas Vagas de Testador de software Vagas de Economista Vagas de Diretor de vendas Vagas de Diretor comercial Vagas de Analista de RH Vagas de Historiador Vagas de Auditor interno Vagas de Direito Vagas de Auxiliar financeiro Vagas de Docente Vagas de Copywriter Vagas de Advogado Vagas de Optometrista LinkedIn © 2026 Sobre Acessibilidade Contrato do Usuário Política de Privacidade do LinkedIn Política de Cookies Política de Direitos Autorais Política da Marca Controles de visitantes Diretrizes da Comunidade العربية (Árabe) বাংলা (Bengali) Čeština (Tcheco) Dansk (Dinamarquês) Deutsch (Alemão) Ελληνικά (Grego) English (Inglês) Español (Espanhol) فارسی (Persa) Suomi (Finlandês) Français (Francês) हिंदी (Hindi) Magyar (Húngaro) Bahasa Indonésia (Indonésio) Italiano (Italiano) עברית (Hebraico) 日本語 (Japonês) 한국어 (Coreano) मराठी (Marati) Bahasa Malaysia (Malaio) Nederlands (Holandês) Norsk (Norueguês) ਪੰਜਾਬੀ (Punjabi) Polski (Polonês) Português (Português) Română (Romeno) Русский (Russo) Svenska (Sueco) తెలుగు (Telugu) ภาษาไทย (Tailandês) Tagalog (Tagalog) Türkçe (Turco) Українська (Ucraniano) Tiếng Việt (Vietnamita) 简体中文 (Chinês (Simplificado)) 正體中文 (Chinês (Tradicional)) Idioma Aceite e cadastre-se no LinkedIn Ao clicar em Continuar para se cadastrar ou entrar, você aceita o Contrato do Usuário , a Política de Privacidade e a Política de Cookies do LinkedIn. Entre para ver quem você já conhece na empresa Cloudflare Entrar Olá novamente E-mail ou telefone Senha Exibir Esqueceu a senha? Entrar ou Ao clicar em Continuar para se cadastrar ou entrar, você aceita o Contrato do Usuário , a Política de Privacidade e a Política de Cookies do LinkedIn. Nunca usou o LinkedIn? Cadastre-se agora ou Nunca usou o LinkedIn? Cadastre-se agora Ao clicar em Continuar para se cadastrar ou entrar, você aceita o Contrato do Usuário , a Política de Privacidade e a Política de Cookies do LinkedIn. | 2026-01-13T09:29:16 |
https://confluence.atlassian.com/spaces/BAMKB/pages/179443464/Bamboo+Knowledge+Base | Bamboo Knowledge Base | Bamboo | Atlassian Documentation Products Bamboo Support Documentation Knowledge base Resources Search Log in View account View requests Log out ... Knowledge base Products Jira Software Project and issue tracking Jira Service Management Service management and customer support Jira Work Management Manage any business project Confluence Document collaboration Bitbucket Git code management See all Resources Documentation Usage and admin help Community Answers, support, and inspiration Suggestions and bugs Feature suggestions and bug reports Marketplace Product apps Billing and licensing Frequently asked questions Log out Log in to account Contact support Training & Certification Cloud Migration Center GDPR guides Enterprise services Atlassian partners Developers User groups Automation for Jira Atlassian.com Page View in Confluence Edit Page Viewport Manage Viewport Confluence Dashboard Space Directory People Directory Atlassian Support Bamboo Knowledge Base Bamboo Knowledge Base Find troubleshooting and how-to articles for Bamboo Recently Created and Updated Articles How to retrieve Bamboo Data Center permissions through REST API and SQL Queries updated Jul 04, 2025 view change How to enable Global Variables REST API updated Jun 30, 2025 view change Manually upgrading the PostgreSQL version of your Amazon RDS database from 9.5 (and below) to 9.6 updated Jun 30, 2025 view change How to Enable Detailed SQL Logging updated Jun 30, 2025 view change How to obtain and identify on Bamboo Datacenter the list of the test cases for the plans and specific buildresults updated Jun 30, 2025 view change Show More Need more help? Contact Support Visit the Atlassian Community or Atlassian Developer Community Developer Support Service Desk Looking for Atlassian Partner for custom request? Powered by Confluence and Scroll Viewport . Atlassian Notice at Collection Privacy Policy Terms of Use Security © Atlassian | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/saviynt-intelligence/ | Saviynt Intelligence | LinkedIn Skip to main content LinkedIn Saviynt in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Saviynt Intelligence Identity & Access Management (IAM) Software by Saviynt See who's skilled in this Add as skill Get started Report this product About Saviynt Intelligence delivers multilayered identity security insights and analytics through pioneering machine learning and generative AI capabilities. Gain unparalleled control of identity security throughout your security program to boost productivity, improve compliance, and be audit-ready with the industry’s most innovative AI/ML capabilities. Media Products media viewer No more previous content Better Understand Your Security Posture Easily dive into risky behaviors and access to understand intermediate questionable activity. A Friend to Help You Along the Way Simply start a conversation to get support and complete tasks. A Friend to Help You Along the Way Allow Saviynt to take on administrator workloads. Enable One Identity for Life Easily assess potential duplicates and merge them into a single record. Gain a Better Understanding of Enterprise Risk Instantly see why requests will likely be approved or denied based on several factors. No more next content Similar products Crowd Crowd Identity & Access Management (IAM) Software Cloudflare Access Cloudflare Access Identity & Access Management (IAM) Software Akamai Identity Cloud Akamai Identity Cloud Identity & Access Management (IAM) Software RSA Governance & Lifecycle RSA Governance & Lifecycle Identity & Access Management (IAM) Software Veridian Veridian Identity & Access Management (IAM) Software Teleport Teleport Identity & Access Management (IAM) Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/company/cloudflare?trk=products_seo_search | Cloudflare | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join now for free Cloudflare Computer and Network Security San Francisco, California 1,123,490 followers At Cloudflare, we have our eyes set on an ambitious goal — to help build a better Internet. See jobs Follow Discover all 6,532 employees Report this company Overview Jobs Life About us Cloudflare, Inc. (NYSE: NET) is the leading connectivity cloud company. It empowers organizations to make their employees, applications and networks faster and more secure everywhere, while reducing complexity and cost. Cloudflare’s connectivity cloud delivers the most full-featured, unified platform of cloud-native products and developer tools, so any organization can gain the control they need to work, develop, and accelerate their business. Powered by one of the world’s largest and most interconnected networks, Cloudflare blocks billions of threats online for its customers every day. It is trusted by millions of organizations – from the largest brands to entrepreneurs and small businesses to nonprofits, humanitarian groups, and governments across the globe. Website https://www.cloudflare.com External link for Cloudflare Industry Computer and Network Security Company size 1,001-5,000 employees Headquarters San Francisco, California Type Public Company Founded 2009 Specialties nginx, lua, go, web performance, web security, dns, network, noc, nocc, ddos, CDN, waf, zero trust security, and developer tools Products See all No more previous content Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Identity & Access Management (IAM) Software Cloudflare Access Identity & Access Management (IAM) Software Cloudflare CDN, Content Delivery Network (CDN) Software Cloudflare CDN Content Delivery Network (CDN) Software Cloudflare DDoS Protection, DDoS Protection Software Cloudflare DDoS Protection DDoS Protection Software Cloudflare DNS, Managed DNS Services Software Cloudflare DNS Managed DNS Services Software Cloudflare Load Balancing, Load Balancing Software Cloudflare Load Balancing Load Balancing Software Cloudflare Registrar, Managed DNS Services Software Cloudflare Registrar Managed DNS Services Software Cloudflare Spectrum, DDoS Protection Software Cloudflare Spectrum DDoS Protection Software Cloudflare SSL / TLS, SSL Certificates Software Cloudflare SSL / TLS SSL Certificates Software Cloudflare Stream, Live Streaming Software Cloudflare Stream Live Streaming Software No more next content Products Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Identity & Access Management (IAM) Software Cloudflare Access Identity & Access Management (IAM) Software Cloudflare CDN, Content Delivery Network (CDN) Software Cloudflare CDN Content Delivery Network (CDN) Software Cloudflare DDoS Protection, DDoS Protection Software Cloudflare DDoS Protection DDoS Protection Software Cloudflare DNS, Managed DNS Services Software Cloudflare DNS Managed DNS Services Software Cloudflare Load Balancing, Load Balancing Software Cloudflare Load Balancing Load Balancing Software Cloudflare Registrar, Managed DNS Services Software Cloudflare Registrar Managed DNS Services Software Cloudflare Spectrum, DDoS Protection Software Cloudflare Spectrum DDoS Protection Software Cloudflare SSL / TLS, SSL Certificates Software Cloudflare SSL / TLS SSL Certificates Software Cloudflare Stream, Live Streaming Software Cloudflare Stream Live Streaming Software Cloudflare WAF, Web Application Firewalls (WAF) Cloudflare WAF Web Application Firewalls (WAF) Cloudflare Web Analytics, Digital Analytics Software Cloudflare Web Analytics Digital Analytics Software Cloudflare Workers, Server Virtualization Software Cloudflare Workers Server Virtualization Software Locations Primary 101 Townsend St San Francisco, California 94107, US Get directions Westminster Bridge Road 6th Floor, Riverside Building, County Hall London, England SE1 7PB, GB Get directions 120 Robinson Road Frasers Tower #35-01 Singapore, Singapore 069547, SG Get directions 405 Comal St Austin, Texas 78702, US Get directions 10 Almaden Blvd Suite 200 San Jose, California 95113, US Get directions Rosental 7 Munich, Bavaria 80331, DE Get directions 301 N Neil St Suite 440 Champaign, Illinois 61820, US Get directions 26-1 Sakuragaoka-cho Shibuya-ku, Level 15 Cerulean Tower Tokyo, 150-8512, JP Get directions 16 South Guangshun Street Donghuang Building 17th Floor Beijing, Chaoyang District Beijing 100015, CN Get directions Rue de la Loi 38 Brussels, Brussels Region 1000, BE Get directions Praça Marquês de Pombal 14 7th floor Lisbon, 1250-162, PT Get directions 6, Place de la Madeleine Mailing Address Only Paris, Île-de-France 75008, FR Get directions 20 Martin Place Level 10 Sydney, NSW 2000, AU Get directions 1401 K St NW Washington, District of Columbia 20005, US Get directions Show more locations Show fewer locations Employees at Cloudflare Adam Edgmond Mark Nottingham Trevor Laughton Carl Ledbetter See all employees Updates Cloudflare 1,123,490 followers 8h Report this post As we kick off the new year, we’re spotlighting Cloudflare leaders across multiple functions who will share their insights around technical trends and emerging threats in 2026. 🎥 Nan Hao Maguire, APAC & Japan Field CTO at Cloudflare, breaks down the urgent shifts in the threat landscape, from smarter AI-driven attacks to the emerging reality of quantum computing. Discover our technical predictions for 2026 in our Post Quantum Computing solution brief: https://cfl.re/3LyW1eC #Cybersecurity #QuantumComputing #AI #FutureofTech #Infrastructure #2026Trends …more 25 2 Comments Like Comment Share Cloudflare 1,123,490 followers 14h Report this post The margin is thinner than you think with modernizing applications. 📉 14% are behind schedule. 13% are ahead of schedule. This 1% difference can make or break your ability to innovate with AI. 🤖 Find out how in the 2026 Cloudflare App Innovation Report, dropping this Wednesday. 🚀 #AppInnovationReport #TechnologyInnovation #CyberSecurity 35 4 Comments Like Comment Share Cloudflare 1,123,490 followers 3d Report this post 🤠 Dallas! The future of connectivity is coming to Frisco. Ready to connect with the leaders driving network modernization right here in Texas? Join us for Cloudflare Immerse Dallas on February 12th! We’re bringing together the region’s top security, IT, and digital leaders for an afternoon of deep dives into the Connectivity Cloud, Zero Trust, and AI application security. It’s more than just sessions—it’s your chance to network with peers and get your toughest questions answered at our "Ask the Cloudflare Experts" bar. 📍 Where: HALL Park Hotel, Frisco, TX 📅 When: Thursday, Feb 12, 2026 | 1:30 PM - 5:00 PM (Happy Hour to follow! 🍹) Spots are limited. Secure your seat today! 👇 https://lnkd.in/dEKuBqve #CloudflareImmerse #DallasTech #NetSec #FriscoTX #Networking #CyberSecurity #ConnectivityCloud 50 4 Comments Like Comment Share Cloudflare 1,123,490 followers 4d Report this post What's your preferred method for knowledge sharing within a team (e.g., detailed READMEs, synchronous workshops, pairing)? #CloudflareChat 29 8 Comments Like Comment Share Cloudflare 1,123,490 followers 4d Report this post We are thrilled to announce that Cloudflare has been recognized as the current Company to Beat in the December 2025 Gartner AI Vendor Race for Edge Distribution Platform AI! Discover the key findings of the report from our article 👇 Cloudflare named as the current Company to Beat in a Gartner® report for Edge Distribution Platform AI! Cloudflare on LinkedIn 657 11 Comments Like Comment Share Cloudflare 1,123,490 followers 5d Edited Report this post Cloudflare is getting ready for ICE 2026 in Barcelona, taking place 19–21 January. We’ll be at Booth 4K30 sharing how Cloudflare for iGaming helps platforms deliver fast, secure, and reliable experiences for players around the world. If you’re attending, stop by to meet the team, explore our iGaming security solutions, and join us for a relaxed Happy Hour at the booth. If you pre-book a meeting with us, you’ll also be entered into a prize draw for a chance to win an exclusive FC Barcelona jersey on the first day of the event! Click here to book your meeting: https://lnkd.in/gSPe58K6 See you there! 33 Like Comment Share Cloudflare 1,123,490 followers 5d Report this post Is your organization struggling to manage a sprawling attack surface across hybrid environments? Join Cloudflare and Werner Executive VP & CIO Daragh Mahon to hear directly from one of our customers on their successful real-world Zero Trust deployments. Learn more about priority use cases, common challenges, and architectural strategies. Register today! https://lnkd.in/db4Gb6Rk #ZeroTrust #Cybersecurity #Cloudflare #Webinar 41 2 Comments Like Comment Share Cloudflare 1,123,490 followers 5d Report this post Defend against rising app-layer DDoS attacks 📱 In his latest article for theNET, Gregory Van den Top explains how DDoS attacks — often powered by AI — are a growing threat to applications. They can slow or completely crash software, bringing critical operations to a halt. The right strategic framework — focused on detecting, mitigating, and adapting — can help stop attacks and improve resilience: https://lnkd.in/dwuSqcm4 60 1 Comment Like Comment Share Cloudflare 1,123,490 followers 6d Report this post A BGP route leak in Venezuela recently impacted internet connectivity. Our latest analysis breaks down how this happened and why it highlights the need for better routing security across the global Internet. https://cfl.re/4qEaNQ5 A closer look at a BGP anomaly in Venezuela blog.cloudflare.com 358 4 Comments Like Comment Share Cloudflare 1,123,490 followers 6d Report this post Cloudflare was proud to protect the Moldovan Central Election Commission during their elections. 🔗 Learn more about it on our blog: https://lnkd.in/gQ8P2NmB Anatolie Golovco 1w CloudFlare mentioned Moldova in their 2025 Annual Impact Report. As a personal tip to web studios that care about protecting their customers against DDoS attacks: take a look at CloudFlare Pages, CloudFlare R2, and Hugo CMS as alternatives to traditional hosting setups and content management systems. https://lnkd.in/dxgycsYm #CloudFlare 41 2 Comments Like Comment Share Join now to see what you are missing Find people you know at Cloudflare Browse recommended jobs for you View all updates, news, and articles Join now Affiliated pages Cloudflare for Public Sector Computer and Network Security San Francisco, California Cloudflare Partner Network Computer and Network Security Similar pages Akamai Technologies Technology, Information and Internet Cambridge, MA CrowdStrike Computer and Network Security Palo Alto Networks Computer and Network Security SANTA CLARA, California Atlassian Software Development Sydney, NSW Google Software Development Mountain View, CA Zscaler Computer and Network Security San Jose, California Snowflake Software Development Microsoft Software Development Redmond, Washington Cisco Software Development San Jose, CA Databricks Software Development San Francisco, CA Show more similar pages Show fewer similar pages Browse jobs Cloudflare jobs 1,064 open jobs Engineer jobs 555,845 open jobs Manager jobs 1,880,925 open jobs Account Executive jobs 71,457 open jobs Analyst jobs 694,057 open jobs Director jobs 1,220,357 open jobs Account Manager jobs 121,519 open jobs Associate jobs 1,091,945 open jobs Software Engineer jobs 300,699 open jobs Developer jobs 258,935 open jobs Project Manager jobs 253,048 open jobs Sales Manager jobs 310,050 open jobs Sales Director jobs 83,949 open jobs Vice President jobs 235,270 open jobs Intern jobs 71,196 open jobs President jobs 92,709 open jobs Executive jobs 690,514 open jobs Specialist jobs 768,666 open jobs Enterprise Account Executive jobs 44,389 open jobs Head jobs 1,018,536 open jobs Show more jobs like this Show fewer jobs like this More searches More searches Cloudflare jobs Engineer jobs Manager jobs Director jobs Account Executive jobs Analyst jobs Account Manager jobs Software Engineer jobs Developer jobs Sales Director jobs Sales Manager jobs Project Manager jobs Technical Account Manager jobs Vice President jobs Intern jobs Senior Software Engineer jobs Associate jobs Solutions Engineer jobs Executive jobs Specialist jobs Business Development Representative jobs Senior Director jobs Enterprise Account Executive jobs Head jobs Consultant jobs Engineering Manager jobs Business Development Specialist jobs Partner jobs Recruiter jobs Scientist jobs President jobs Solutions Architect jobs Marketing Manager jobs Senior Manager jobs Program Manager jobs Site Reliability Engineer jobs Full Stack Engineer jobs Data Analyst jobs Operational Specialist jobs Customer Success Manager jobs Cyber Security Specialist jobs Sales Specialist jobs Sales Technician jobs Python Developer jobs Machine Learning Engineer jobs Product Manager jobs Administrator jobs Human Resources Specialist jobs Support Engineer jobs Head of Sales jobs Director of Engineering jobs Channel Account Manager jobs Lead jobs Data Engineer jobs Vice President of Sales jobs Strategic Account Manager jobs Human Resources Business Partner jobs Senior Product Manager jobs Marketing Director jobs Human Resources Manager jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Cloudflare Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=JDS2BnIAAAAJ&hl=en | Jeffrey Li - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 전체 2021년 이후 서지정보 834 817 h-index 8 8 i10-index 8 8 0 480 240 120 360 2020 2021 2022 2023 2024 2025 2026 16 38 72 62 156 478 9 공개 액세스 모두 보기 모두 보기 자료 3개 자료 0개 공개 비공개 재정 지원 요구사항 기준 공동 저자 Ameet Talwalkar CMU, Datadog cmu.edu의 이메일 확인됨 Mikhail Khodak UW-Madison cs.princeton.edu의 이메일 확인됨 Gregory Plumb Carnegie Mellon University andrew.cmu.edu의 이메일 확인됨 Valerie Chen Carnegie Mellon University cmu.edu의 이메일 확인됨 Joon Sik Kim ML Research @ DynamoAI; PhD @ CMU alumni.cmu.edu의 이메일 확인됨 Sebastian Caldas Google google.com의 이메일 확인됨 팔로우 Jeffrey Li University of Washington cs.washington.edu의 이메일 확인됨 - 홈페이지 Machine Learning 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 DataComp-LM: In search of the next generation of training sets for language models J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, S Gadre, H Bansal, E Guha, ... arXiv preprint arXiv:2406.11794 , 2024 302 * 2024 Differentially private meta-learning J Li, M Khodak, S Caldas, A Talwalkar arXiv preprint arXiv:1909.05830 , 2019 184 2019 OpenThoughts: Data Recipes for Reasoning Models E Guha, R Marten, S Keh, N Raoof, G Smyrnis, H Bansal, M Nezhurina, ... arXiv preprint arXiv:2506.04178 , 2025 126 * 2025 Interpretable machine learning: Moving from mythos to diagnostics V Chen, J Li, JS Kim, G Plumb, A Talwalkar Communications of the ACM 65 (8), 43-50 , 2022 93 2022 Language models scale reliably with over-training and on downstream tasks SY Gadre, G Smyrnis, V Shankar, S Gururangan, M Wortsman, R Shao, ... arXiv preprint arXiv:2403.08540 , 2024 76 2024 A learning theoretic perspective on local explainability J Li, V Nagarajan, G Plumb, A Talwalkar arXiv preprint arXiv:2011.01205 , 2020 21 2020 TiC-LM: A web-scale benchmark for time-continual LLM pretraining J Li, M Armandpour, SI Mirzadeh, S Mehta, V Shankar, R Vemulapalli, ... Proceedings of the 63rd Annual Meeting of the Association for Computational�… , 2025 10 * 2025 Characterizing the impacts of semi-supervised learning for weak supervision J Li, J Zhang, L Schmidt, AJ Ratner Advances in Neural Information Processing Systems 36, 4309-4330 , 2023 10 2023 Better alignment with instruction back-and-forth translation T Nguyen, J Li, S Oh, L Schmidt, JE Weston, L Zettlemoyer, X Li Findings of the Association for Computational Linguistics: EMNLP 2024, 13289�… , 2024 8 2024 Language models improve when pretraining data matches target tasks D Mizrahi, ABL Larsen, J Allardice, S Petryk, Y Gorokhov, J Li, A Fang, ... arXiv preprint arXiv:2507.12466 , 2025 4 2025 Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks T Zhang, L Cai, J Li, N Roberts, N Guha, F Sala Advances in Neural Information Processing Systems 37, 122292-122315 , 2024 2024 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–11 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://visualstudio.microsoft.com/ko/vs/ | Visual Studio IDE - 코딩 디버깅 및 테스트를 위한 AI 주 콘텐츠로 건너뛰기 Microsoft Visual Studio Visual Studio Visual Studio 홈 개발자 도구 Visual Studio Visual Studio 개요 기능 버전 확장 시작 서비스 상태 FAQ 지원 설명서 블로그 Visual Studio Code Visual Studio Code 개요 확장 지원 설명서 블로그 VS Code for Education 다운로드 구입 구독 개요 지원 관리자 포털 구독자 포털 Dev Essentials Visual Studio 허브 자세히 무료 Visual Studio Microsoft 전체 Global Microsoft Security Azure Dynamics 365 Microsoft 365 Microsoft Teams Windows 365 기술 및 혁신 기술 및 혁신 AI Azure Space 혼합 현실 Microsoft HoloLens Microsoft Viva 양자 컴퓨팅 지속 가능성 산업 분야 산업 분야 교육 자동차 금융 서비스 정부 기관 의료 제조업 소매 모든 산업 파트너 파트너 파트너 찾기 파트너 되기 파트너 네트워크 Microsoft Marketplace Marketplace Rewards Software development companies 더 많은 정보 더 많은 정보 블로그 Microsoft Advertising 개발자 센터 설명서 이벤트 라이선스 Microsoft Learn Microsoft Research 사이트맵 보기 로그인 This device is not currently supported for these products. Visual Studio IDE Visual Studio for Mac Visual Studio Code To continue downloading, click here Visual Studio IDE – 코딩 디버깅 및 테스트를 위한 AI 2025-12-08T11:35:54-08:00 AI로 더욱 스마트해진 강력한 IDE 에이전트 모드 – 이제 GitHub Copilot Free (무료)에서 사용 가능 문제를 해결하고, 다음 단계를 조정하며, 변경 내용을 적용하고, 오류를 반복하는 AI 기반 코딩 지원을 경험해 보세요. Visual Studio 다운로드 Community Professional Enterprise Insiders 체험판 시작하기 생산성 향상 AI 지원 에이전트 모드를 사용하는 실제 AI 솔루션 단일 프롬프트에서 모두 계획, 빌드, 테스트 및 수정하세요. 자연어로 요구 사항을 설명하면 나머지는 Copilot이 알아서 처리합니다. Visual Studio에서 나가지 않고 linter, 테스트 및 명령을 실행하세요. 지금 에이전트 모드 활성화 항상 최신 AI 모델 최신 AI 모델에 액세스하여 채팅 또는 인라인에서 가장 정확하고 상황에 맞는 제안을 받아보세요. 각 작업의 필요에 맞는 모델을 선택하세요. 최신 모델 가져오기 무료이며 Visual Studio에 완전히 통합됨 Visual Studio에 통합된 AI 기반 코딩 지원입니다. 2,000개의 코드 완성을 받으세요. 매월 50개의 채팅 메시지를 무료로 받으세요. Copilot Free (무료) 사용 GitHub Copilot의 작동 보기 커밋 메시지를 다시 작성하지 않음: GitHub Copilot에게 감사드립니다. Visual Studio에서 GitHub Copilot을 사용한 다중 파일 편집 Visual Studio에서 GitHub Copilot 무료 시작하기 모든 Visual Studio를 최신 상태로 유지 Visual Studio 허브 방문 개발 디버그 테스트 버전 제어 협업 클라우드 디자인 프로필 데이터 Copilot: 쌍 프로그래머 한 줄 또는 전체 코드 조각에 대한 컨텍스트 인식 코드 완성 제안으로 개발 속도를 높이세요. 코드 검토, 파일 내 미리보기, 롤백 환경을 갖춘 Copilot 편집을 사용하여 여러 파일을 편집하세요. 코드 제안을 위해 Copilot을 사용하는 방법 채팅을 통해 코드 및 쿼리에 대한 지원 받기 GitHub Copilot Chat으로 코딩 쿼리에 대한 실시간 도움을 받으세요. 대화형 채팅 인터페이스는 개발 환경 내에서 즉각적인 컨텍스트 인식 제안을 제공하고, 디버깅을 지원하며, 단위 테스트를 생성합니다. Copilot 채팅 결과를 개선하기 위한 팁 Copilot을 사용하여 쉽게 디버깅 AI가 제공하는 코드에 대한 심층적인 인사이트를 통해 디버깅을 가속화하세요. Copilot은 예외, 교착 상태 및 기타 디버깅 시나리오에 대한 심층적인 분석과 설명을 제공하여 대상에 맞는 솔루션을 제공합니다. 디버깅 프로세스 간소화 Copilot를 통해 테스트 효율성 향상 수동 테스트 생성 및 코드 품질 유지에 소요되는 시간을 줄이세요. Copilot의 자동화는 기존 코드를 기반으로 단위 및 통합 테스트를 통해 오류를 조기에 식별하여 안정성을 개선하는 데 도움이 됩니다. Copilot을 사용하여 오류 수정 Copilot을 활용하여 버전 관리 간소화 코드 변경에 따라 AI 생성 커밋 메시지를 사용하여 깔끔하고 조직된 코드베이스를 유지하세요. GitHub Copilot은 워크플로, 브랜치 관리 및 병합 충돌을 명확히 하여 버전 관리를 간소화합니다. GitHub Copilot 채팅을 사용하여 커밋 메시지 생성 화면 이상의 공유 Live Share의 실시간 공동 작업 세션은 언어나 플랫폼에 관계없이 팀의 편집 및 디버깅 주기를 단축합니다. 액세스 제어 및 사용자 지정 편집기 설정이 포함된 개인 설정된 세션을 통해 모든 사람이 코드 일관성을 유지할 수 있습니다. Live Share를 통한 공동 작업 Visual Studio의 Azure Visual Studio에서 Azure를 사용하여 빌드, 배포 및 확장하세요: 통합 도구와 AI 기능을 사용하여 클라우드 우선 애플리케이션을 효율적이고 안전하게 만들 수 있으며, 이 모든 것이 IDE 내에서 가능합니다. 웹앱, API 또는 AI 기반 솔루션을 개발하든 관계없이 Visual Studio 간소화된 코딩 환경을 위한 원활한 Azure 통합을 제공합니다. 자습서를 살펴보고, 코딩 수준을 높이고, Azure DevOps 및 GitHub 액션을 사용하여 배포를 자동화하세요. Visual Studio의 강력한 도구를 사용하여 Azure 서비스에 연결하고, 애플리케이션을 배포하고, 실시간으로 디버깅하세요. Visual Studio에서 Azure에 대해 자세히 알아보기 멋진 플랫폼 간 앱 디자인 Visual Studio는 Windows, Mac, Linux, iOS 및 Android용 최신 크로스 플랫폼 애플리케이션을 빌드하는 데 가장 적합한 IDE입니다. 복잡한 레이아웃을 단순화하고 UI에 생동감을 불어넣는 강력한 비주얼 디자이너를 사용하여 WinForms, WPF, WinUI 및 MAUI로 풍부한 클라이언트 앱을 만들 수 있습니다. 시각화 및 모델링 기본 제공 프로파일링 도구로 빠르고 반응성이 뛰어난 앱을 빌드하세요 Visual Studio의 프로파일링 도구를 사용하여 웹 및 클라이언트를 위한 빠르고 응답성이 뛰어난 .NET 및 C++ 애플리케이션을 빌드하세요. CPU, 메모리, XAML, 데이터베이스, 이벤트 등에 대한 프로파일러를 사용하면 성능 문제를 식별하고 해결하는 데 도움이 되는 완전한 도구 모음을 갖게 됩니다. 앱 성능 측정 SQL을 간편하게 해 주는 도구 IDE를 벗어나지 않고 SQL 프로젝트로 작업합니다. 풍부한 편집 환경으로 쿼리를 작성하고 서버와 데이터베이스를 보고 탐색합니다. Visual Studio 내에서 데이터베이스 스키마 및 쿼리를 모두 시각화합니다. Visual Studio에서의 데이터 액세스 나만의 항목으로 만들기 최신 개발 도구에서 기대하는 것처럼 구성하고 테마를 지정합니다. 이미 설치된 기본 테마 중 하나를 선택하든 Visual Studio Marketplace에서 새 테마를 탐색하든 상관없이 편집기나 IDE를 자유롭게 만들 수 있습니다. 테마 살펴보기 확장 프로그램으로 더 많이 활용하기 확장은 기존 도구에 대한 추가 설정, 기능 또는 사용을 포함하여 Visual Studio를 사용자 지정하고 향상시키는 추가 기능입니다. 마켓플레이스에 있는 수천 개의 확장 프로그램을 통해 생산성을 높이고 워크플로를 충족할 수 있는 다양한 옵션이 있습니다. 확장 살펴보기 GitHub Actions 설치 Visual Studio에서 열린 솔루션의 현재 리포지토리에 대한 GitHub Actions 보기를 제공하는 창입니다. @timheuer 제공 확장 받기 Markdown Editor v2 설치 라이브 미리 보기 및 구문 강조 표시가 포함된 완전한 기능을 갖춘 Markdown 편집기입니다. GitHub Flavored Markdown을 지원합니다. 확장 받기 Visual Studio 테마 팩 설치 현재 Visual Studio에서 사용할 수 있는 인기 있는 테마 모음입니다. 자세한 정보 SQLite 및 SQL Server Compact 도구 상자 설치 이 확장은 포함된 데이터베이스 개발 작업을 돕는 몇 가지 기능을 추가합니다. 확장 받기 Visual Studio Community 학생, 오픈 소스 및 개인 개발자를 위한 모든 기능을 갖춘 무료 IDE입니다. 추가 정보 무료 다운로드 Visual Studio Professional 효율적인 소규모 팀 협업을 위한 강력한 개발자 도구, 서비스 및 구독 혜택입니다. 자세한 정보 무료 평가판 Visual Studio Enterprise 클라우드에 대한 Azure 크레딧과 개발/테스트 가격 책정이 포함된 고급 디버깅, 엔터프라이즈 보안, AI 지원 개발입니다. 자세한 정보 무료 평가판 팔로우하기 Dev Essentials Developer Community 블로그: Visual Studio .NET C++ 새로운 기능 Surface Pro Surface Laptop 조직용 Copilot 개인 사용자용 Copilot Microsoft 365 Microsoft 제품 살펴보기 Windows 11 앱 Microsoft Store 계정 프로필 다운로드 센터 Microsoft Store 지원 반품/환불 주문 조회 교육 Microsoft Education 교육용 장치 교육용 Microsoft Teams Microsoft 365 Education Office Education 교육자 트레이닝 및 개발 학생 및 학부모용 특가 혜택 Azure for students 기업 고객 Microsoft Security Azure Dynamics 365 Microsoft 365 Microsoft Advertising Microsoft 365 Copilot Microsoft Teams 개발자 및 IT Microsoft 개발자 Microsoft Learn AI 마켓플레이스 앱 지원 Microsoft Tech 커뮤니티 Microsoft Marketplace Microsoft Power Platform Marketplace Rewards Visual Studio 회사 채용 정보 Microsoft 정보 회사 뉴스 Microsoft 개인 정보 보호 투자자 지속 가능성 한국어(대한민국) 개인정보처리방침 선택 옵트아웃 아이콘 개인 정보 선택 사항 개인정보처리방침 선택 옵트아웃 아이콘 개인 정보 선택 사항 소비자 상태 개인정보처리방침 문의처 개인정보처리방침 쿠키 관리 사용 조건 상표 광고에 대한 내용 © Microsoft 2026 한국마이크로소프트(유) 대표이사: 조원우 주소: (우)110-150 서울 종로구 종로1길 50 더 케이트윈타워 A동 12층 전화번호: 02-531-4500, 메일: ms-korea@microsoft.com 사업자등록번호: 120-81-05948 사업자정보확인 호스팅서비스 제공자: Microsoft Corporation 통신판매신고: 제2013-서울종로-1009호 사이버몰의 이용약관: Microsoft Store 판매 약관 | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/hclsoftware-hcl-domino/?trk=products_seo_search | HCL Domino | LinkedIn Skip to main content LinkedIn HCLSoftware in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in HCL Domino Business Process Management Software by HCLSoftware See who's skilled in this Add as skill Learn more Report this product About HCL Domino is an enterprise-grade and secure application development platform designed to solve workflow and process challenges — fast. It powers more than 10 million apps transforming the business of more than 15,000 customers. Domino is more modern and offers more value and lower TCO than ever. Now you can make your apps mobile with zero effort and build new ones 70% faster than before. Domino also provides an enterprise-grade mail, calendar, and contacts platform. The platform is associated with Notes, a professional secure on-premises client which allows users to execute the enterprise applications from their desktop (including the mail client), in a connected or disconnected way. This product is intended for Application Architect Application Development Manager Chief Technical Officer Head Business System Lotus Notes Consultant Domino Administrator Business Application Consultant Lotus Domino Administrator Domino Developer Lotus Notes Domino Developer Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less HCLSoftware products HCL BigFix HCL BigFix Endpoint Detection & Response (EDR) Software HCL Commerce+ HCL Commerce+ E-Commerce Platforms HCL Connections HCL Connections Enterprise Social Networking Software HCL Digital Experience HCL Digital Experience Digital Experience Platforms (DXP) HCL Mainframe Solutions HCL Mainframe Solutions Mainframe Management Software HCL Sametime HCL Sametime Employee Communications Software HCL Software DevOps HCL Software DevOps DevOps Software HCL Unica HCL Unica Marketing Automation Software HCL Volt MX HCL Volt MX Low-Code Development Platforms Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/zoho-fsm/ | Zoho FSM | LinkedIn Skip to main content LinkedIn Zoho in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Zoho FSM Field Service Management (FSM) Software by Zoho See who's skilled in this Add as skill Learn more Report this product About Zoho FSM is a field service management platform that automates the entire spectrum of field operations. It streamlines work order management, eases scheduling and dispatching, improves workforce productivity, and simplifies invoicing and payments. It also has a mobile app for Android and iOS that lets field agents access data, log work, and collaborate with the office from the job site. This product is intended for Field Service Technician Field Service Specialist Field Service Manager Field Service Supervisor Field Service Coordinator Dispatcher Director of Field Services Senior Field Service Technician Senior Field Service Engineer Field Service Representative Media Products media viewer No more previous content FSM Overview with CRM Zoho FSM offers a host of features that help increase first-time fix rates, minimize costs, and maximize revenue in your field service business. From receiving a service request to raising an invoice, Zoho FSM optimizes every aspect of the business. This video gives you an overview of all the features in Zoho FSM with a quick look at how to use them. Advanced Work Order Management Enter service requests, send cost estimates, create work orders with multiple services and tasks, and add service appointments. You can also turn work orders into invoices with a click. The Dispatch Console for Scheduling and Dispatching The Dispatch Console is the task board for scheduling and dispatching. It has 3 views - Gantt, Map, and Calendar. The map view shows the live locations of field agents. Schedules can be created on the Calendar or Gantt with a simple drag and drop. Improved Workforce Management View the details of your workforce in the Users tab. See their calendars, trip details, time-offs, and other information. Add skills and territorial coverage for each user. Create Crews with multiple technicians. The Zoho FSM Mobile App to Work on the Go The mobile app lets field agents check in, see their appointments, log trips and timesheets, and share notes and images. It also enables creating service reports, raising invoices, and taking up follow-up jobs. No more next content Similar products Atenea Atenea Field Service Management (FSM) Software Field Nation Premier Field Nation Premier Field Service Management (FSM) Software FieldEdge by Xplor FieldEdge by Xplor Field Service Management (FSM) Software Simpro Simpro Field Service Management (FSM) Software Wello Solutions Wello Solutions Field Service Management (FSM) Software Zuper Zuper Field Service Management (FSM) Software Sign in to see more Show more Show less Zoho products Bigin by Zoho CRM Bigin by Zoho CRM Customer Relationship Management (CRM) Software Zoho Analytics Zoho Analytics Business Intelligence (BI) Software Zoho Commerce Zoho Commerce E-Commerce Platforms Zoho DataPrep Zoho DataPrep Data Preparation Tools Zoho Forms Zoho Forms Online Form Builder Software Zoho One Zoho One Business Management Software Zoho People Zoho People Human Resources Management Systems (HRMS) Zoho RPA Zoho RPA Robotic Process Automation (RPA) Software Zoho Webinar Zoho Webinar Webinar Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?modality=modality:text&p=99&sort=trending | Text Datasets – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":401131,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities Reset Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 401,131 Full-text search Edit filters Sort: Trending Active filters: text Clear all HuggingFaceFW/finetranslations Viewer • Updated 4 days ago • 3.33B • 7.34k • 143 xiuhuywh/DRIM-VisualReasonHard Viewer • Updated 4 days ago • 17.1k • 1.8k • 96 WNT3D/Ultimate-Offensive-Red-Team Viewer • Updated Aug 23, 2025 • 25.6k • 481 • 120 xiuhuywh/DRIM-ColdstartSFT Viewer • Updated 4 days ago • 44.3k • 4.93k • 84 miromind-ai/MiroVerse-v0.1 Viewer • Updated Nov 19, 2025 • 228k • 767 • 177 123olp/binance-futures-ohlcv-2018-2026 Viewer • Updated 2 days ago • 425M • 478 • 96 DatologyAI/DatBench Viewer • Updated 2 days ago • 43.5k • 286 • 68 MiniMaxAI/OctoCodingBench Viewer • Updated about 5 hours ago • 72 • 68 Salesforce/wikitext Viewer • Updated Jan 4, 2024 • 3.71M • 793k • 616 ScienceOne-AI/S1-MMAlign Viewer • Updated 8 days ago • 21.1M • 7.54k • 70 TeichAI/glm-4.7-2000x Viewer • Updated 21 days ago • 1.98k • 339 • 71 facebook/research-plan-gen Viewer • Updated 11 days ago • 22.5k • 3.61k • 272 OpenDataArena/ODA-Mixture-500k Viewer • Updated about 22 hours ago • 506k • 5.49k • 116 nvidia/embed-nemotron-dataset-v1 Viewer • Updated 1 day ago • 12.8M • 204 • 50 DatologyAI/DatBench-Full Viewer • Updated 7 days ago • 195k • 231 • 46 OpenDataArena/ODA-Math-460k Viewer • Updated 13 days ago • 460k • 4.93k • 96 tatsu-lab/alpaca Viewer • Updated May 22, 2023 • 52k • 44.6k • 889 missvector/linux-commands Viewer • Updated about 16 hours ago • 71.8k • 617 • 84 OpenDataArena/ODA-Mixture-100k Viewer • Updated 13 days ago • 101k • 3.56k • 90 Anthropic/hh-rlhf Viewer • Updated May 26, 2023 • 169k • 22.7k • 1.63k Rapidata/bananamark-dataset Viewer • Updated Dec 12, 2025 • 2.16k • 62 • 28 wikimedia/wikipedia Viewer • Updated Jan 9, 2024 • 61.6M • 74.6k • 1.12k TeichAI/claude-4.5-opus-high-reasoning-250x Viewer • Updated Nov 28, 2025 • 250 • 8.33k • 161 openmed-community/MedReason-Stenographic Viewer • Updated 4 days ago • 31.5k • 34 • 22 m-a-p/COIG-CQIA Viewer • Updated Apr 18, 2024 • 44.7k • 5.12k • 691 HuggingFaceFW/finepdfs Viewer • Updated 4 days ago • 476M • 23.2k • 711 Bingguang/HardGen Viewer • Updated 5 days ago • 17k • 281 • 65 MiniMaxAI/VIBE Viewer • Updated 21 days ago • 200 • 10.5k • 249 MLCommons/peoples_speech Viewer • Updated Nov 20, 2024 • 8.05M • 13.6k • 246 LEMAS-Project/LEMAS-Dataset-train Viewer • Updated 4 days ago • 125M • 3.62k • 15 Previous 1 2 3 ... 100 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?modality=modality%3Adocument | Document Datasets – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":1333,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities Reset Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 1,333 Full-text search Edit filters Sort: Trending Active filters: document Clear all opendatalab/ScienceMetaBench Preview • Updated 1 day ago • 3.45k • 99 Mtechlaw/TfGBV-Grok-NCII-Dataset Viewer • Updated 6 days ago • 1 • 101 • 10 openai/gdpval Viewer • Updated Sep 25, 2025 • 220 • 26.3k • 436 gaia-benchmark/GAIA Viewer • Updated Oct 28, 2025 • 932 • 16.3k • 588 camel-ai/seta-env Viewer • Updated about 21 hours ago • 3 • 603 • 5 jbarrow/CommonForms Viewer • Updated Nov 16, 2025 • 487k • 1.45k • 50 nick007x/arxiv-papers Viewer • Updated Oct 14, 2025 • 2.55M • 10.1k • 163 d4rk3r/resumes-raw-pdf Viewer • Updated Nov 13, 2024 • 1.94k • 1.35k • 13 ArtificialAnalysis/AA-Omniscience-Public Viewer • Updated Nov 20, 2025 • 600 • 1k • 23 Forceless/Zenodo10K Viewer • Updated Oct 31, 2025 • 10.4k • 4.78k • 19 xywang1/NaturalConv Viewer • Updated Nov 7, 2024 • 19.9k • 284 • 13 meldynamics/liepa-tts Viewer • Updated 6 days ago • 20.2k • 31 • 1 SUFE-AIFLM-Lab/FinGAIA Viewer • Updated Jul 22, 2025 • 13 • 240 • 1 ArkaMukherjee/reasoning-10k-v2 Viewer • Updated Nov 8, 2025 • 10k • 67 • 2 qualcomm/M3Kang Viewer • Updated Dec 5, 2025 • 149k • 45 • 1 yyyang/SlideTailor-PSP-dataset Viewer • Updated 3 days ago • 80 • 143 • 2 mercor/APEX-v1-extended Viewer • Updated Dec 5, 2025 • 100 • 675 • 5 jkdkr2439/cot-probability-constriction Viewer • Updated 4 days ago • 1 • 20 • 1 fengzhang/fzTestDatasets Viewer • Updated Nov 11, 2021 • 1 • 36 huggingface-legal/takedown-notices Viewer • Updated Nov 12, 2025 • 10 • 897 • 28 NitishKarra/Nitishh Viewer • Updated Aug 3, 2022 • 59 • 19 Aunderline/CMeEE-V2 Viewer • Updated Oct 23, 2022 • 23k • 342 • 8 MayaGalvez/linguistic_representation_mBERT Viewer • Updated Jan 26, 2023 • 1 • 25 silentmobius28/consolidated_appropriations_act_2023 Viewer • Updated Dec 23, 2022 • 1 • 15 fmi-unibuc/RoLiDi Viewer • Updated Apr 24, 2024 • 10 • 204 • 5 lucianistrati/RoLiDi Viewer • Updated Apr 24, 2024 • 10 • 102 DanteMerlino/ENT-papers Viewer • Updated Jan 29, 2023 • 2 • 92 Sjagnik/LazyBooks Viewer • Updated Mar 29, 2023 • 1 • 25 sharad36/beat Viewer • Updated May 23, 2023 • 21 • 213 AyoubChLin/northwind_invocies Viewer • Updated Apr 6, 2023 • 831 • 1.03k • 1 Previous 1 2 3 ... 45 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fstratsys-strategic-planning&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/vultr-block-storage/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_image-click | Vultr Block Storage | LinkedIn Skip to main content LinkedIn Vultr in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Vultr Block Storage Block Storage Software by Vultr See who's skilled in this Add as skill Learn more Report this product About Create expandable HDD or NVMe SSD storage volumes and mount them directly to your compute instances. Similar products Tencent Cloud Block Storage Tencent Cloud Block Storage Block Storage Software OVHcloud Block Storage OVHcloud Block Storage Block Storage Software DigitalOcean Block Storage DigitalOcean Block Storage Block Storage Software Vultr Vultr Block Storage Software Vultr Bare Metal Vultr Bare Metal Block Storage Software DataCore SANsymphony DataCore SANsymphony Block Storage Software Sign in to see more Show more Show less Vultr products Vultr Vultr Block Storage Software Vultr Bare Metal Vultr Bare Metal Block Storage Software LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/legal/cookie-policy?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Fenterprise-social-networking-software&trk=registration-frontend_join-form-cookie-policy | Cookie Policy | LinkedIn Skip to main content User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws Cookie Policy Effective on June 3, 2022 At LinkedIn, we believe in being clear and open about how we collect and use data related to you. This Cookie Policy applies to any LinkedIn product or service that links to this policy or incorporates it by reference. We use cookies and similar technologies such as pixels, local storage and mobile ad IDs (collectively referred to in this policy as “cookies”) to collect and use data as part of our Services, as defined in our Privacy Policy (“Services”) and which includes our sites, communications, mobile applications and off-site Services, such as our ad services and the “Apply with LinkedIn” and “Share with LinkedIn” plugins or tags. In the spirit of transparency, this policy provides detailed information about how and when we use these technologies. By continuing to visit or use our Services, you are agreeing to the use of cookies and similar technologies for the purposes described in this policy. What technologies are used? ENTER A SUMMARY Type of technology Description Cookies A cookie is a small file placed onto your device that enables LinkedIn features and functionality. Any browser visiting our sites may receive cookies from us or cookies from third parties such as our customers, partners or service providers. We or third parties may also place cookies in your browser when you visit non-LinkedIn sites that display ads or that host our plugins or tags . We use two types of cookies: persistent cookies and session cookies. A persistent cookie lasts beyond the current session and is used for many purposes, such as recognizing you as an existing user, so it’s easier to return to LinkedIn and interact with our Services without signing in again. Since a persistent cookie stays in your browser, it will be read by LinkedIn when you return to one of our sites or visit a third party site that uses our Services. Session cookies last only as long as the session (usually the current visit to a website or a browser session). Pixels A pixel is a tiny image that may be embedded within web pages and emails, requiring a call (which provides device and visit information) to our servers in order for the pixel to be rendered in those web pages and emails. We use pixels to learn more about your interactions with email content or web content, such as whether you interacted with ads or posts. Pixels can also enable us and third parties to place cookies on your browser. Local storage Local storage enables a website or application to store information locally on your device(s). Local storage may be used to improve the LinkedIn experience, for example, by enabling features, remembering your preferences and speeding up site functionality. Other similar technologies We also use other tracking technologies, such as mobile advertising IDs and tags for similar purposes as described in this Cookie Policy. References to similar technologies in this policy includes pixels, local storage, and other tracking technologies. Our cookie tables lists cookies and similar technologies that are used as part of our Services. Please note that the names of cookies and similar technologies may change over time. What are these technologies used for? Below we describe the purposes for which we use these technologies. ENTER SUMMARY Purpose Description Authentication We use cookies and similar technologies to recognize you when you visit our Services. If you’re signed into LinkedIn, these technologies help us show you the right information and personalize your experience in line with your settings. For example, cookies enable LinkedIn to identify you and verify your account. Security We use cookies and similar technologies to make your interactions with our Services faster and more secure. For example, we use cookies to enable and support our security features, keep your account safe and to help us detect malicious activity and violations of our User Agreement. Preferences, features and services We use cookies and similar technologies to enable the functionality of our Services, such as helping you to fill out forms on our Services more easily and providing you with features, insights and customized content in conjunction with our plugins. We also use these technologies to remember information about your browser and your preferences. For example, cookies can tell us which language you prefer and what your communications preferences are. We may also use local storage to speed up site functionality. Customized content We use cookies and similar technologies to customize your experience on our Services. For example, we may use cookies to remember previous searches so that when you return to our services, we can offer additional information that relates to your previous search. Plugins on and off LinkedIn We use cookies and similar technologies to enable LinkedIn plugins both on and off the LinkedIn sites. For example, our plugins, including the "Apply with LinkedIn" button or the "Share" button may be found on LinkedIn or third-party sites, such as the sites of our customers and partners. Our plugins use cookies and other technologies to provide analytics and recognize you on LinkedIn and third-party sites. If you interact with a plugin (for instance, by clicking "Apply"), the plugin will use cookies to identify you and initiate your request to apply. You can learn more about plugins in our Privacy Policy . Advertising Cookies and similar technologies help us show relevant advertising to you more effectively, both on and off our Services and to measure the performance of such ads. We use these technologies to learn whether content has been shown to you or whether someone who was presented with an ad later came back and took an action (e.g., downloaded a white paper or made a purchase) on another site. Similarly, our partners or service providers may use these technologies to determine whether we've shown an ad or a post and how it performed or provide us with information about how you interact with ads. We may also work with our customers and partners to show you an ad on or off LinkedIn, such as after you’ve visited a customer’s or partner’s site or application. These technologies help us provide aggregated information to our customers and partners. For further information regarding the use of cookies for advertising purposes, please see Sections 1.4 and 2.4 of the Privacy Policy . As noted in Section 1.4 of our Privacy Policy, outside Designated Countries , we also collect (or rely on others who collect) information about your device where you have not engaged with our Services (e.g., ad ID, IP address, operating system and browser information) so we can provide our Members with relevant ads and better understand their effectiveness. For further information, please see Section 1.4 of the Privacy Policy . Analytics and research Cookies and similar technologies help us learn more about how well our Services and plugins perform in different locations. We or our service providers use these technologies to understand, improve, and research products, features and services, including as you navigate through our sites or when you access LinkedIn from other sites, applications or devices. We or our service providers, use these technologies to determine and measure the performance of ads or posts on and off LinkedIn and to learn whether you have interacted with our websites, content or emails and provide analytics based on those interactions. We also use these technologies to provide aggregated information to our customers and partners as part of our Services. If you are a LinkedIn member but logged out of your account on a browser, LinkedIn may still continue to log your interaction with our Services on that browser until the expiration of the cookie in order to generate usage analytics for our Services. We may share these analytics in aggregate form with our customers. What third parties use these technologies in connection with our Services? Third parties such as our customers, partners and service providers may use cookies in connection with our Services. For example, third parties may use cookies in their LinkedIn pages, job posts and their advertisements on and off LinkedIn for their own marketing purposes. For an illustration, please visit LinkedIn’s Help Center . Third parties may also use cookies in connection with our off-site Services, such as LinkedIn ad services. Third parties may use cookies to help us to provide our Services. We may also work with third parties for our own marketing purposes and to enable us to analyze and research our Services. Your Choices You have choices on how LinkedIn uses cookies and similar technologies. Please note that if you limit the ability of LinkedIn to set cookies and similar technologies, you may worsen your overall user experience, since it may no longer be personalized to you. It may also stop you from saving customized settings like login information. Opt out of targeted advertising As described in Section 2.4 of the Privacy Policy , you have choices regarding the personalized ads you may see. LinkedIn Members can adjust their settings here . Visitor controls can be found here . Some mobile device operating systems such as Android provide the ability to control the use of mobile advertising IDs for ads personalization. You can learn how to use these controls by visiting the manufacturer’s website. We do not use iOS mobile advertising IDs for targeted advertising. Browser Controls Most browsers allow you to control cookies through their settings, which may be adapted to reflect your consent to the use of cookies. Further, most browsers also enable you to review and erase cookies, including LinkedIn cookies. To learn more about browser controls, please consult the documentation that your browser manufacturer provides. What is Do Not Track (DNT)? DNT is a concept that has been promoted by regulatory agencies such as the U.S. Federal Trade Commission (FTC), for the Internet industry to develop and implement a mechanism for allowing Internet users to control the tracking of their online activities across websites by using browser settings. As such, LinkedIn does not generally respond to “do not track” signals. Other helpful resources To learn more about advertisers’ use of cookies, please visit the following links: Internet Advertising Bureau (US) European Interactive Digital Advertising Alliance (EU) Internet Advertising Bureau (EU) LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?modality=modality:text&p=2&sort=trending | Text Datasets – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":401131,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities Reset Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 401,131 Full-text search Edit filters Sort: Trending Active filters: text Clear all HuggingFaceFW/finetranslations Viewer • Updated 4 days ago • 3.33B • 7.34k • 143 xiuhuywh/DRIM-VisualReasonHard Viewer • Updated 4 days ago • 17.1k • 1.8k • 96 WNT3D/Ultimate-Offensive-Red-Team Viewer • Updated Aug 23, 2025 • 25.6k • 481 • 120 xiuhuywh/DRIM-ColdstartSFT Viewer • Updated 4 days ago • 44.3k • 4.93k • 84 miromind-ai/MiroVerse-v0.1 Viewer • Updated Nov 19, 2025 • 228k • 767 • 177 123olp/binance-futures-ohlcv-2018-2026 Viewer • Updated 2 days ago • 425M • 478 • 96 DatologyAI/DatBench Viewer • Updated 2 days ago • 43.5k • 286 • 68 MiniMaxAI/OctoCodingBench Viewer • Updated about 5 hours ago • 72 • 68 Salesforce/wikitext Viewer • Updated Jan 4, 2024 • 3.71M • 793k • 616 ScienceOne-AI/S1-MMAlign Viewer • Updated 8 days ago • 21.1M • 7.54k • 70 TeichAI/glm-4.7-2000x Viewer • Updated 21 days ago • 1.98k • 339 • 71 facebook/research-plan-gen Viewer • Updated 11 days ago • 22.5k • 3.61k • 272 OpenDataArena/ODA-Mixture-500k Viewer • Updated about 22 hours ago • 506k • 5.49k • 116 nvidia/embed-nemotron-dataset-v1 Viewer • Updated 1 day ago • 12.8M • 204 • 50 DatologyAI/DatBench-Full Viewer • Updated 7 days ago • 195k • 231 • 46 OpenDataArena/ODA-Math-460k Viewer • Updated 13 days ago • 460k • 4.93k • 96 tatsu-lab/alpaca Viewer • Updated May 22, 2023 • 52k • 44.6k • 889 missvector/linux-commands Viewer • Updated about 16 hours ago • 71.8k • 617 • 84 OpenDataArena/ODA-Mixture-100k Viewer • Updated 13 days ago • 101k • 3.56k • 90 Anthropic/hh-rlhf Viewer • Updated May 26, 2023 • 169k • 22.7k • 1.63k Rapidata/bananamark-dataset Viewer • Updated Dec 12, 2025 • 2.16k • 62 • 28 wikimedia/wikipedia Viewer • Updated Jan 9, 2024 • 61.6M • 74.6k • 1.12k TeichAI/claude-4.5-opus-high-reasoning-250x Viewer • Updated Nov 28, 2025 • 250 • 8.33k • 161 openmed-community/MedReason-Stenographic Viewer • Updated 4 days ago • 31.5k • 34 • 22 m-a-p/COIG-CQIA Viewer • Updated Apr 18, 2024 • 44.7k • 5.12k • 691 HuggingFaceFW/finepdfs Viewer • Updated 4 days ago • 476M • 23.2k • 711 Bingguang/HardGen Viewer • Updated 5 days ago • 17k • 281 • 65 MiniMaxAI/VIBE Viewer • Updated 21 days ago • 200 • 10.5k • 249 MLCommons/peoples_speech Viewer • Updated Nov 20, 2024 • 8.05M • 13.6k • 246 LEMAS-Project/LEMAS-Dataset-train Viewer • Updated 4 days ago • 125M • 3.62k • 15 Previous 1 2 3 ... 100 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#students | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/dataport-a%C3%B6r-dataportai/?trk=products_details_guest_other_products_by_org_section_product_link_result-card_full-click#main-content | data[port]ai | LinkedIn Skip to main content LinkedIn Dataport AöR in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in data[port]ai Data Science & Machine Learning Platforms by Dataport AöR See who's skilled in this Add as skill Learn more Report this product About data[port]ai ist Ihr Wissens- und Lösungshub für Daten, KI-Technologien und sicheren Betrieb. Sie erhalten Zugang zu leistungsstarken KI-Werkzeugen wie großen Sprachmodellen (LLM), Chatbots sowie automatischer Sprach-, Bild- und Texterkennung. Ihre Vorteile mit Dataport: modernste Infrastruktur, höchste Datensicherheit, Souveränität und eine starke Trägergemeinschaft. Auf einen Blick: ✅ KI-Lösungen ✅ Plattformleistungen ✅ Beratung This product is intended for Machine Learning Specialist Data Scientist Artificial Intelligence Consultant Artificial Intelligence Engineer Artificial Intelligence Specialist Product Manager DevOps Engineer Media Products media viewer No more previous content data[port]ai Aus Daten Chancen machen No more next content Similar products Amazon SageMaker Amazon SageMaker Data Science & Machine Learning Platforms The Databricks Data Intelligence Platform The Databricks Data Intelligence Platform Data Science & Machine Learning Platforms ZAIDYN ZAIDYN Data Science & Machine Learning Platforms Dataiku Dataiku Data Science & Machine Learning Platforms Datalore Datalore Data Science & Machine Learning Platforms DataRobot DataRobot Data Science & Machine Learning Platforms Sign in to see more Show more Show less Dataport AöR products Dataport Consulting Dataport Consulting Strategic Planning Software dDataBox dDataBox Managed File Transfer (MFT) Software dMessenger dMessenger Enterprise Messaging Software dProjectTracking dProjectTracking Project Management Software dWebService dWebService Web Hosting dWorkflow dWorkflow Workflow Management Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://visualstudio.microsoft.com/zh-hans/vs/ | Visual Studio IDE - 用于编码调试和测试的 AI 跳转至主内容 Microsoft Visual Studio Visual Studio Visual Studio 主页 开发人员工具 Visual Studio Visual Studio 概述 功能 版本 扩展 开始 服务状态 常见问题解答支持 文档 博客 Visual Studio Code Visual Studio Code 概述 扩展 支持 文档 博客 VS Code 教育版 下载 购买 订阅 概述 支持 管理员门户 订阅者门户 Dev Essentials Visual Studio 中心 更多 免费 Visual Studio 所有 Microsoft Global Microsoft 安全 Azure Dynamics 365 Microsoft 365 Microsoft Teams Windows 365 技术和创新 技术和创新 AI Azure Space 混合现实 Microsoft HoloLens Microsoft Viva 量子计算 可持续发展 工业 工业 教育 汽车 金融服务 政府 医疗保健 制造业 零售业 所有行业 合作伙伴 合作伙伴 查找合作伙伴 成为合作伙伴 合作伙伴网络 Microsoft Marketplace Marketplace Rewards Software development companies 资源 资源 博客 Microsoft Advertising 开发人员中心 文档 活动 许可 Microsoft Learn Microsoft Research 查看站点地图 登录 This device is not currently supported for these products. Visual Studio IDE Visual Studio for Mac Visual Studio Code To continue downloading, click here Visual Studio IDE – 用于编码调试和测试的 AI 2025-12-08T11:35:55-08:00 强大的 IDE，通过 AI 变得更加智能 智能体模式 – 现已在 GitHub Copilot Free 中提供 体验 AI 支持的编码帮助以分析问题原因、协调后续步骤、应用更改并对错误进行迭代优化。 下载 Visual Studio Community Professional Enterprise Insiders 免费试用 提高生产力的 AI 协助 使用智能体模式的实际 AI 解决方案 计划、生成、测试和修复 – 通过一个提示全部完成。 使用自然语言描述你的需求，让 Copilot 执行其余操作。 无需离开 Visual Studio，即可运行 linter、测试和命令。 立即激活智能体模式 始终保持最新的 AI 模型 访问最新的 AI 模型，在聊天或内联中获取最准确的上下文感知建议。 选择一个模型以匹配每个任务的需求。 获取最新模型 在 Visual Studio 中免费且完全集成 AI 支持的编码协助，集成到 Visual Studio 中。 接收 2,000 个代码补全。 每月免费获取 50 条聊天消息。 启用 Copilot Free 观看 GitHub Copilot 的实际运作 不必再编写提交消息: 感谢 GitHub Copilot Visual Studio 中 GitHub Copilot 的多文件编辑 Visual Studio 中的 GitHub Copilot Free 入门 随时了解 Visual Studio 所有最新动态 访问 Visual Studio 中心 开发 调试 测试 版本控制 协作 云 设计 个人资料 数据 Copilot: 你的配对程序员 使用单行或整个代码片段的上下文感知代码补全建议加速开发。 通过代码评审、文件内预览和回滚体验，使用 Copilot Edits 进行多文件编辑。 如何将 Copilot 用于代码建议 聊天以获取有关代码和查询的帮助 通过 GitHub Copilot 对话助手获取编码查询的实时帮助。 对话聊天界面提供即时上下文感知建议、帮助调试和生成单元测试，所有这些都在开发环境中。 改进 Copilot 对话助手结果的提示 通过 Copilot 轻松调试 通过对代码的深入见解(由 AI 提供支持)加速调试。 Copilot 提供深入的分析和说明，为异常、死锁和其他调试方案提供针对性解决方案。 简化调试过程 通过 Copilot 提高测试效率 减少手动创建测试和维护代码质量所花费的时间。 Copilot 的自动化可帮助你提高可靠性，基于现有代码在单元测试和集成测试中尽早识别错误。 使用 Copilot 修复错误 利用 Copilot 简化版本控制 使用基于代码更改的 AI 生成的提交消息维护干净有序的代码库。 GitHub Copilot 通过确保工作流、分支管理和合并冲突的清晰度来简化版本控制。 使用 GitHub Copilot 对话助手生成提交消息 共享不止于屏幕 无论使用哪种语言或平台，Live Share 的实时协作会话均可加快团队的编辑和调试周期。 具有访问控制和自定义编辑器设置的个性化会话可以确保每个人保持代码一致。 使用 Live Share 协作 Visual Studio 中的 Azure 在 Visual Studio 中使用 Azure 进行构建、部署和缩放: 使用集成工具和 AI 功能高效、安全地创建云优先的应用程序—全部在 IDE 中完成。 无论是开发 Web 应用、API 还是 AI 驱动的解决方案，Visual Studio 都能提供无缝的 Azure 集成，以获得简化的编码体验。 浏览教程、提升编码技术，并使用 Azure DevOps 和 GitHub Actions 自动执行部署。 使用 Visual Studio 强大的工具连接到 Azure 服务、部署应用程序、进行实时调试。 详细了解 Visual Studio 中的 Azure 设计精美的跨平台应用 Visual Studio 是构建适用于 Windows、Mac、Linux、iOS 和 Android 的新式跨平台应用程序的最佳 IDE。 使用功能强大的视觉设计器，通过 WinForms、WPF、WinUI 和 MAUI 创建丰富的客户端应用，从而简化复杂的布局并使 UI 生动起来。 可视化和建模 使用内置 分析工具构建快速且响应性良好的应用 使用 Visual Studio 中的分析工具构建适用于 Web 和客户端的响应迅速且灵敏的 .NET 和 C++ 应用程序。 借助面向 CPU、内存、XAML、数据库和事件等的探查器等，你可以使用一整套工具来帮助你识别和解决性能问题。 度量应用性能 让创建 SQL 变得轻而易举的工具 无需离开 IDE 即可处理 SQL 项目。 使用丰富的编辑体验构建查询，查看和浏览服务器与数据库。 只需在 Visual Studio 内即可实现数据库架构和查询的可视化。 在 Visual Studio 中访问数据 个性化设置 配置和主题的设置，符合你对任何新式开发工具所期待的需求。无论是选择已安装的一个默认主题，还是从 Visual Studio Marketplace 探索新主题，都可自由地对编辑器或 IDE 进行适合你的个性化设置。 浏览主题 使用扩展进行进一步操作 扩展是自定义和增强 Visual Studio 的加载项，包括额外的设置、功能或现有工具的用途。 市场上有数以千计的扩展产品，提供大量提高生产力和满足工作流的选择。 浏览扩展 GitHub Actions 安装 一个窗口，它为 Visual Studio 中打开的解决方案的当前存储库提供 GitHub Actions 视图。 由 @timheuer 提供 获取扩展 Markdown editor v2 安装 全功能 Markdown editor，具有实时预览和语法突出显示功能。 支持 GitHub 风格的 Markdown。 获取扩展 Visual Studio 主题包 安装 热门主题的集合，现在可用于 Visual Studio。 了解更多 SQLite 和 SQL Server Compact 工具包 安装 此扩展添加了多个功能，可帮助你完成嵌入式数据库开发工作。 获取扩展 Visual Studio Community 面向学生、开放源代码和个人开发人员的全功能免费 IDE。 了解更多 免费下载 Visual Studio Professional 强大的开发人员工具、服务和订阅权益，可实现高效的小型团队协作。 了解详细信息 免费试用 Visual Studio Enterprise 高级调试、企业安全性、AI 辅助开发，以及面向云的 Azure 额度和开发/测试定价。 了解详细信息 免费试用 关注我们 Dev Essentials Developer Community 博客: Visual Studio .NET C++ 新增内容 Surface Pro Surface Laptop 适用于组织的 Copilot Microsoft 365 探索 Microsoft 产品 Windows 11 应用程序 Microsoft Store 帐户个人资料 下载中心 订单跟踪 教育 Microsoft 教育版 教育设备 Microsoft Teams 教育版 Microsoft 365 教育版 Office 教育版 教育工作者培训和开发 面向学生和家长的优惠 面向学生的 Azure 企业 Microsoft 安全 Azure Dynamics 365 Microsoft 365 Microsoft Advertising Microsoft 365 Copilot Microsoft Teams 开发人员与 IT Microsoft 开发人员 Microsoft Learn 支持 AI 商城应用 Microsoft 技术社区 Microsoft Marketplace Microsoft Power Platform Marketplace Rewards Visual Studio 公司 招贤纳士 关于 Microsoft 公司新闻 Microsoft 隐私 投资人 可持续发展 中文(中国) 你的隐私选择选择退出图标 你的隐私选择 你的隐私选择选择退出图标 你的隐私选择 消费者健康隐私 请联系我们 隐私 & Cookie 管理 Cookie 使用条款 商标 关于我们的广告 © Microsoft 2026 | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#companies | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#foreword | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Flarksuite-lark%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://au.linkedin.com/company/cloudflare | Cloudflare | LinkedIn Skip to main content LinkedIn Articles People Learning Jobs Games Sign in Create an account Cloudflare Computer and Network Security San Francisco, California 1,123,490 followers At Cloudflare, we have our eyes set on an ambitious goal — to help build a better Internet. See jobs Follow Discover all 6,532 employees Report this company Overview Jobs Life About us Cloudflare, Inc. (NYSE: NET) is the leading connectivity cloud company. It empowers organizations to make their employees, applications and networks faster and more secure everywhere, while reducing complexity and cost. Cloudflare’s connectivity cloud delivers the most full-featured, unified platform of cloud-native products and developer tools, so any organization can gain the control they need to work, develop, and accelerate their business. Powered by one of the world’s largest and most interconnected networks, Cloudflare blocks billions of threats online for its customers every day. It is trusted by millions of organizations – from the largest brands to entrepreneurs and small businesses to nonprofits, humanitarian groups, and governments across the globe. Website https://www.cloudflare.com External link for Cloudflare Industry Computer and Network Security Company size 1,001-5,000 employees Headquarters San Francisco, California Type Public Company Founded 2009 Specialties nginx, lua, go, web performance, web security, dns, network, noc, nocc, ddos, CDN, waf, zero trust security, and developer tools Products See all No more previous content Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Identity & Access Management (IAM) Software Cloudflare Access Identity & Access Management (IAM) Software Cloudflare CDN, Content Delivery Network (CDN) Software Cloudflare CDN Content Delivery Network (CDN) Software Cloudflare DDoS Protection, DDoS Protection Software Cloudflare DDoS Protection DDoS Protection Software Cloudflare DNS, Managed DNS Services Software Cloudflare DNS Managed DNS Services Software Cloudflare Load Balancing, Load Balancing Software Cloudflare Load Balancing Load Balancing Software Cloudflare Registrar, Managed DNS Services Software Cloudflare Registrar Managed DNS Services Software Cloudflare Spectrum, DDoS Protection Software Cloudflare Spectrum DDoS Protection Software Cloudflare SSL / TLS, SSL Certificates Software Cloudflare SSL / TLS SSL Certificates Software Cloudflare Stream, Live Streaming Software Cloudflare Stream Live Streaming Software No more next content Products Argo Smart Routing, Network Management Software Argo Smart Routing Network Management Software Cloudflare Access, Identity & Access Management (IAM) Software Cloudflare Access Identity & Access Management (IAM) Software Cloudflare CDN, Content Delivery Network (CDN) Software Cloudflare CDN Content Delivery Network (CDN) Software Cloudflare DDoS Protection, DDoS Protection Software Cloudflare DDoS Protection DDoS Protection Software Cloudflare DNS, Managed DNS Services Software Cloudflare DNS Managed DNS Services Software Cloudflare Load Balancing, Load Balancing Software Cloudflare Load Balancing Load Balancing Software Cloudflare Registrar, Managed DNS Services Software Cloudflare Registrar Managed DNS Services Software Cloudflare Spectrum, DDoS Protection Software Cloudflare Spectrum DDoS Protection Software Cloudflare SSL / TLS, SSL Certificates Software Cloudflare SSL / TLS SSL Certificates Software Cloudflare Stream, Live Streaming Software Cloudflare Stream Live Streaming Software Cloudflare WAF, Web Application Firewalls (WAF) Cloudflare WAF Web Application Firewalls (WAF) Cloudflare Web Analytics, Digital Analytics Software Cloudflare Web Analytics Digital Analytics Software Cloudflare Workers, Server Virtualization Software Cloudflare Workers Server Virtualization Software Locations Primary 101 Townsend St San Francisco, California 94107, US Get directions Westminster Bridge Road 6th Floor, Riverside Building, County Hall London, England SE1 7PB, GB Get directions 120 Robinson Road Frasers Tower #35-01 Singapore, Singapore 069547, SG Get directions 405 Comal St Austin, Texas 78702, US Get directions 10 Almaden Blvd Suite 200 San Jose, California 95113, US Get directions Rosental 7 Munich, Bavaria 80331, DE Get directions 301 N Neil St Suite 440 Champaign, Illinois 61820, US Get directions 26-1 Sakuragaoka-cho Shibuya-ku, Level 15 Cerulean Tower Tokyo, 150-8512, JP Get directions 16 South Guangshun Street Donghuang Building 17th Floor Beijing, Chaoyang District Beijing 100015, CN Get directions Rue de la Loi 38 Brussels, Brussels Region 1000, BE Get directions Praça Marquês de Pombal 14 7th floor Lisbon, 1250-162, PT Get directions 6, Place de la Madeleine Mailing Address Only Paris, Île-de-France 75008, FR Get directions 20 Martin Place Level 10 Sydney, NSW 2000, AU Get directions 1401 K St NW Washington, District of Columbia 20005, US Get directions Show more locations Show fewer locations Employees at Cloudflare Adam Edgmond Mark Nottingham Trevor Laughton Carl Ledbetter See all employees Updates Cloudflare 1,123,490 followers 8h Report this post As we kick off the new year, we’re spotlighting Cloudflare leaders across multiple functions who will share their insights around technical trends and emerging threats in 2026. 🎥 Nan Hao Maguire, APAC & Japan Field CTO at Cloudflare, breaks down the urgent shifts in the threat landscape, from smarter AI-driven attacks to the emerging reality of quantum computing. Discover our technical predictions for 2026 in our Post Quantum Computing solution brief: https://cfl.re/3LyW1eC #Cybersecurity #QuantumComputing #AI #FutureofTech #Infrastructure #2026Trends …more 25 2 Comments Like Comment Share Cloudflare 1,123,490 followers 14h Report this post The margin is thinner than you think with modernizing applications. 📉 14% are behind schedule. 13% are ahead of schedule. This 1% difference can make or break your ability to innovate with AI. 🤖 Find out how in the 2026 Cloudflare App Innovation Report, dropping this Wednesday. 🚀 #AppInnovationReport #TechnologyInnovation #CyberSecurity 35 4 Comments Like Comment Share Cloudflare 1,123,490 followers 3d Report this post 🤠 Dallas! The future of connectivity is coming to Frisco. Ready to connect with the leaders driving network modernization right here in Texas? Join us for Cloudflare Immerse Dallas on February 12th! We’re bringing together the region’s top security, IT, and digital leaders for an afternoon of deep dives into the Connectivity Cloud, Zero Trust, and AI application security. It’s more than just sessions—it’s your chance to network with peers and get your toughest questions answered at our "Ask the Cloudflare Experts" bar. 📍 Where: HALL Park Hotel, Frisco, TX 📅 When: Thursday, Feb 12, 2026 | 1:30 PM - 5:00 PM (Happy Hour to follow! 🍹) Spots are limited. Secure your seat today! 👇 https://lnkd.in/dEKuBqve #CloudflareImmerse #DallasTech #NetSec #FriscoTX #Networking #CyberSecurity #ConnectivityCloud 50 4 Comments Like Comment Share Cloudflare 1,123,490 followers 4d Report this post What's your preferred method for knowledge sharing within a team (e.g., detailed READMEs, synchronous workshops, pairing)? #CloudflareChat 29 8 Comments Like Comment Share Cloudflare 1,123,490 followers 4d Report this post We are thrilled to announce that Cloudflare has been recognized as the current Company to Beat in the December 2025 Gartner AI Vendor Race for Edge Distribution Platform AI! Discover the key findings of the report from our article 👇 Cloudflare named as the current Company to Beat in a Gartner® report for Edge Distribution Platform AI! Cloudflare on LinkedIn 657 11 Comments Like Comment Share Cloudflare 1,123,490 followers 5d Edited Report this post Cloudflare is getting ready for ICE 2026 in Barcelona, taking place 19–21 January. We’ll be at Booth 4K30 sharing how Cloudflare for iGaming helps platforms deliver fast, secure, and reliable experiences for players around the world. If you’re attending, stop by to meet the team, explore our iGaming security solutions, and join us for a relaxed Happy Hour at the booth. If you pre-book a meeting with us, you’ll also be entered into a prize draw for a chance to win an exclusive FC Barcelona jersey on the first day of the event! Click here to book your meeting: https://lnkd.in/gSPe58K6 See you there! 33 Like Comment Share Cloudflare 1,123,490 followers 5d Report this post Is your organization struggling to manage a sprawling attack surface across hybrid environments? Join Cloudflare and Werner Executive VP & CIO Daragh Mahon to hear directly from one of our customers on their successful real-world Zero Trust deployments. Learn more about priority use cases, common challenges, and architectural strategies. Register today! https://lnkd.in/db4Gb6Rk #ZeroTrust #Cybersecurity #Cloudflare #Webinar 41 2 Comments Like Comment Share Cloudflare 1,123,490 followers 5d Report this post Defend against rising app-layer DDoS attacks 📱 In his latest article for theNET, Gregory Van den Top explains how DDoS attacks — often powered by AI — are a growing threat to applications. They can slow or completely crash software, bringing critical operations to a halt. The right strategic framework — focused on detecting, mitigating, and adapting — can help stop attacks and improve resilience: https://lnkd.in/dwuSqcm4 60 1 Comment Like Comment Share Cloudflare 1,123,490 followers 6d Report this post A BGP route leak in Venezuela recently impacted internet connectivity. Our latest analysis breaks down how this happened and why it highlights the need for better routing security across the global Internet. https://cfl.re/4qEaNQ5 A closer look at a BGP anomaly in Venezuela blog.cloudflare.com 358 4 Comments Like Comment Share Cloudflare 1,123,490 followers 6d Report this post Cloudflare was proud to protect the Moldovan Central Election Commission during their elections. 🔗 Learn more about it on our blog: https://lnkd.in/gQ8P2NmB Anatolie Golovco 1w CloudFlare mentioned Moldova in their 2025 Annual Impact Report. As a personal tip to web studios that care about protecting their customers against DDoS attacks: take a look at CloudFlare Pages, CloudFlare R2, and Hugo CMS as alternatives to traditional hosting setups and content management systems. https://lnkd.in/dxgycsYm #CloudFlare 41 2 Comments Like Comment Share Join now to see what you are missing Find people you know at Cloudflare Browse recommended jobs for you View all updates, news, and articles Join now Affiliated pages Cloudflare for Public Sector Computer and Network Security San Francisco, California Cloudflare Partner Network Computer and Network Security Similar pages Akamai Technologies Technology, Information and Internet Cambridge, MA CrowdStrike Computer and Network Security Palo Alto Networks Computer and Network Security SANTA CLARA, California Atlassian Software Development Sydney, NSW Google Software Development Mountain View, CA Zscaler Computer and Network Security San Jose, California Snowflake Software Development Microsoft Software Development Redmond, Washington Cisco Software Development San Jose, CA Databricks Software Development San Francisco, CA Show more similar pages Show fewer similar pages Browse jobs Cloudflare jobs 52 open jobs Engineer jobs 12,824 open jobs Account Executive jobs 2,265 open jobs Analyst jobs 14,217 open jobs Director jobs 28,989 open jobs Account Manager jobs 3,569 open jobs Software Engineer jobs 5,632 open jobs Developer jobs 5,939 open jobs Project Manager jobs 8,610 open jobs Sales Manager jobs 5,504 open jobs Sales Director jobs 1,241 open jobs Vice President jobs 2,650 open jobs President jobs 331 open jobs Technical Account Manager jobs 1,183 open jobs Marketing Manager jobs 3,259 open jobs Program Manager jobs 4,711 open jobs Scientist jobs 515 open jobs Cyber Security Specialist jobs 532 open jobs Senior Software Engineer jobs 1,571 open jobs Solutions Engineer jobs 3,227 open jobs Show more jobs like this Show fewer jobs like this More searches More searches Cloudflare jobs Engineer jobs Director jobs Account Executive jobs Analyst jobs Account Manager jobs Software Engineer jobs Developer jobs Sales Director jobs Sales Manager jobs Project Manager jobs Technical Account Manager jobs Vice President jobs Senior Software Engineer jobs Solutions Engineer jobs Senior Director jobs Engineering Manager jobs Business Development Specialist jobs Recruiter jobs Scientist jobs President jobs Solutions Architect jobs Marketing Manager jobs Program Manager jobs Site Reliability Engineer jobs Full Stack Engineer jobs Data Analyst jobs Customer Success Manager jobs Cyber Security Specialist jobs Python Developer jobs Machine Learning Engineer jobs Product Manager jobs Human Resources Specialist jobs Head of Sales jobs Director of Engineering jobs Channel Account Manager jobs Data Engineer jobs Vice President of Sales jobs Strategic Account Manager jobs Human Resources Business Partner jobs Senior Product Manager jobs Marketing Director jobs Human Resources Manager jobs Revenue Officer jobs Director of Information Technology jobs Product Designer jobs Senior Program Manager jobs Director of Operations jobs Director of Product Management jobs Vice President of Engineering jobs System Administrator jobs Technical Program Manager jobs Principal Product Manager jobs Customer Director jobs Chief Executive Officer jobs Sales Operations Manager jobs Information Technology Manager jobs Senior Vice President jobs Alliances Manager jobs Head of Marketing jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Cloudflare Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/aha-labs-inc--aha-roadmaps/?trk=products_seo_search#main-content | Aha! Roadmaps | LinkedIn Skip to main content LinkedIn Aha! in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Aha! Roadmaps Strategic Planning Software by Aha! See who's skilled in this Add as skill Try now Report this product About Aha! Roadmaps is the complete product management solution — set strategy, prioritize features, and share visual plans. This product is intended for Product Manager Product Operations Manager Director of Product Management Vice President of Product Management Group Product Manager Chief Innovation Officer Program Manager Project Manager Product Marketing Manager Chief Product Officer Media Products media viewer No more previous content Aha! Roadmaps Watch an an overview of how you can use Aha! Roadmaps to set strategy, crowdsource feedback, prioritize features, and more. Aha! Roadmaps - Strategic vision Define the future of your product. Craft the perfect product strategy so your team can stay aligned around what matters most. Aha! Roadmaps - Ideas portal Capture product ideas in a central place. Make it easy for customers to share feedback through an ideas portal — and automatically stay informed about updates. Aha! Roadmaps - Product value scorecard Determine top priorities based on value. Build out your roadmap with the features that will deliver the greatest impact to your customers. Aha! Roadmaps - Features roadmap Craft a beautiful product roadmap. Quickly create a timeline for what will be delivered and when — and tailor it to specific audiences. No more next content Featured customers of Aha! Roadmaps Experian Information Services 1,665,842 followers Siemens Automation Machinery Manufacturing 8,448,146 followers American Automobile Assoc IT Services and IT Consulting 387 followers LexisNexis IT Services and IT Consulting 390,383 followers LinkedIn Software Development 32,750,448 followers UST IT Services and IT Consulting 1,832,817 followers Similar products Focus Focus Strategic Planning Software DIGITAL PRODUCTS DIGITAL PRODUCTS Strategic Planning Software Cascade Cascade Strategic Planning Software WorkBoard WorkBoard Strategic Planning Software Stratsys platform for compliance and efficiency Stratsys platform for compliance and efficiency Strategic Planning Software Dataport Consulting Dataport Consulting Strategic Planning Software Sign in to see more Show more Show less Aha! products Aha! Academy Aha! Academy Product Management Software Aha! Develop Aha! Develop DevOps Software Aha! Discovery Aha! Discovery Product Management Software Aha! Ideas Aha! Ideas Idea Management Software Aha! Knowledge Aha! Knowledge Knowledge Management Software Aha! Teamwork Aha! Teamwork Project Management Software Aha! Whiteboards Aha! Whiteboards Whiteboard Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://confluence.atlassian.com/bamboo/bamboo-faq-289277293.html | Bamboo FAQ | Bamboo Data Center 12.1 | Atlassian Documentation Products Bamboo Support Documentation Knowledge base Resources Search Log in View account View requests Log out ... Knowledge base Products Jira Software Project and issue tracking Jira Service Management Service management and customer support Jira Work Management Manage any business project Confluence Document collaboration Bitbucket Git code management See all Resources Documentation Usage and admin help Community Answers, support, and inspiration Suggestions and bugs Feature suggestions and bug reports Marketplace Product apps Billing and licensing Frequently asked questions Log out Log in to account Contact support Training & Certification Cloud Migration Center GDPR guides Enterprise services Atlassian partners Developers User groups Automation for Jira Atlassian.com Page View in Confluence Edit Page Viewport Manage Viewport Confluence Dashboard Space Directory People Directory Bamboo latest Documentation Unable to load Atlassian Support Bamboo 12.1 Documentation Bamboo FAQ Data Center 12.1 Versions 12.1 12.0 11.0 10.2 10.1 10.0 9.6 9.5 9.4 See all Bamboo FAQ Bamboo documentation Getting started with Bamboo Installing and upgrading Using Bamboo Bamboo Best Practice Administering Bamboo Bamboo Specs Bamboo FAQ Exporting existing plan configuration to Bamboo YAML Specs Bamboo Data Center On this page In this section Usage FAQ Raising a request with Atlassian Support Support Policies Bamboo resources Glossary Contributing to the Bamboo documentation Related content No related content found Still need help? The Atlassian Community is here for you. Ask the community Bamboo FAQ Answers to commonly raised questions about configuring and using Bamboo: What Is Continuous Integration? Usage FAQ Can multiple plans share a common 3rd-party directory Changing Bamboo database settings Deploying Multiple Atlassian Applications in a Single Tomcat Container How Bamboo processes task arguments and passes them to OS shell Securing your repository connection Changing the remote agent heartbeat interval Cloning a Bamboo instance How do I shut down my elastic instances if I have restarted my Bamboo server How do I stop the Bamboo server from automatically configuring my remote agent's capabilities JUnit parsing in Bamboo Known issues with CVS in Bamboo Monitor Memory usage and Garbage Collection in Bamboo Moving Bamboo-Home of an agent Performing a thread dump Restoring passwords to recover admin users Send Errors to stderr - Script Builder in Visual Studio WinXP to build Solutions Files Using Bamboo with Clover Getting gcov results in Clover coverage summary Working with Java libraries Bamboo indicates that my Ant or Maven builds failed, even though they were successful Raising a request with Atlassian Support Support Policies Bamboo Support Policy New Features Policy Finding Your Bamboo Support Entitlement Number (SEN) Bamboo resources Glossary activity log agent agent-specific capability artifact authors in Bamboo build build activity build duration build log build queue build result build telemetry capability child committer custom capability default repository elastic agent elastic Bamboo elastic block store elastic image elastic instance executable favorites global permission job label parent permission plan plan permission projects in Bamboo queue reason remote agent remote agent supervisor requirement shared capability stage Stock images task triggering watcher Contributing to the Bamboo documentation Need more help? Do you have a question, or need help with Bamboo? Please create a support request . Browse our Bamboo Developer FAQ . You may also like to check out the forums: Bamboo General Forum Bamboo Developers Forum Last modified on Jan 18, 2018 Was this helpful? Yes No It wasn't accurate It wasn't clear It wasn't relevant Provide feedback about this article In this section Usage FAQ Raising a request with Atlassian Support Support Policies Bamboo resources Glossary Contributing to the Bamboo documentation Related content No related content found Powered by Confluence and Scroll Viewport . Atlassian Notice at Collection Privacy Policy Terms of Use Security © Atlassian | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/atlassian-jira/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_image-click#main-content | Jira | LinkedIn Skip to main content LinkedIn Atlassian in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Jira Project Management Software by Atlassian See who's skilled in this Add as skill Learn more Report this product About Plan, track, and deliver your biggest ideas with Jira, the project management tool for all teams. This product is intended for Project Manager Software Engineer Marketing Manager Senior Software Engineer Marketing Director Senior Project Manager Director of Operations Chief Technology Officer Senior Developer Senior Product Manager Media Products media viewer No more previous content Jira Software - Demo See how teams plan, track, release, and report on their work in Jira Software. Boards Visualize all your team’s work on a board. Choose between different agile frameworks like kanban or scrum to manage your workflow. Releases Map your team’s work to releases to understand what’s releasing when and how you’re making progress on each release. Integrations Integrate Jira with all the tools your team uses every day to surface relevant context about work (like real-time updates on the status of code). Roadmaps Connect your team’s work to a product roadmap to track big picture goals for one team or across multiple teams. No more next content Featured customers of Jira Square Software Development 672,363 followers Cisco Software Development 7,318,281 followers eBay Technology, Information and Internet 613,969 followers Airbnb Software Development 3,147,142 followers Spotify Musicians 4,444,653 followers Similar products Trello Trello Project Management Software GitHub Issues GitHub Issues Project Management Software Notion Notion Knowledge Management Software Zoho Projects Zoho Projects Project Management Software Asana Asana Project Management Software Zoho Sprints Zoho Sprints Project Management Software Sign in to see more Show more Show less Atlassian products Bamboo Bamboo DevOps Software Compass Compass DevOps Software Crowd Crowd Identity & Access Management (IAM) Software Fisheye Fisheye Version Control Hosting Software Focus Focus Strategic Planning Software Guard Guard Security Information & Event Management (SIEM) Software Jira Align Jira Align Project Management Software Jira Product Discovery Jira Product Discovery Project Management Software Rovo Rovo Enterprise Search Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/skan-ai-skan-cpx-skan-cognitive-process-discovery-and-operational-intelligence-platform/?trk=products_seo_search | Skan AI Process Intelligence Platform | LinkedIn Skip to main content LinkedIn Skan AI in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Skan AI Process Intelligence Platform Business Process Management Software by Skan AI See who's skilled in this Add as skill Request demo Report this product About See how work really happens across your entire organization. Our platform captures complete end-to-end processes across every application and user, creating accurate digital twins that reveal inefficiencies others miss. Move from guesswork to certainty with continuous monitoring that spots issues before they become costly and validates improvements after implementation. Traditional process discovery tools leave you blind. Process mining only sees what's logged in your systems—missing the human work that makes up most of your operations. Task mining captures individual actions but can't stitch them into complete processes. Skan's Process Intelligence observes everything: every application including mainframes and VDI, every click, every handoff, every variation. We deploy in weeks, not months, with zero system integrations required. You get the full picture of how work flows across any operation. This product is intended for Operations Manager Chief Financial Officer Chief Operating Officer Process Manager Business Process Manager Media Products media viewer No more previous content What is Skan? With Skan’s process intelligence technology, you can now continuously understand how real work is being done. We can help you unlock your business’ potential to be greater at driving operational excellence, business transformation, and continuous improvement. No more next content Featured customers of Skan AI Process Intelligence Platform Drax Group Utilities 56,486 followers Cisive Human Resources Services 29,528 followers Unum Insurance 96,511 followers Dell Technologies Computer Hardware Manufacturing 5,431,605 followers Protective Life Insurance 38,562 followers Mitie Facilities Services 213,757 followers Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/palmirasoftwarehouse-aris/?trk=products_seo_search | ARIS Process Management by Palmira | LinkedIn Skip to main content LinkedIn Palmira Software House in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in ARIS Process Management by Palmira Business Process Management Software by Palmira Software House See who's skilled in this Add as skill Learn more Report this product About Business process analysis your way! ARIS is available in different editions to fit the needs of your organization. Looking to start now with minimal investment? ARIS Elements is designed to kickstart your first process improvement project. ARIS Advanced is designed for those who have reached a level of maturity that requires customization and advanced user management. With ARIS Enterprise you can establish a full-scale enterprise BPA program using the complete ARIS capabilities stack. Media Products media viewer No more previous content ARIS Journey This is a sample of purchase journey in ARIS ARIS Process Mining ARIS helps you read your processes ARIS process modeling You can model your processes in ARIS using different notations, The picture shows the process flow in EPC diagram ARIS Customer Journey Model and analyse every touchpoint in your customer journey No more next content Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Sign in to see more Show more Show less Palmira Software House products ALFABET ALFABET IT Asset Management Software Cloudera Cloudera Big Data Processing & Distribution Software Liferay Liferay Digital Experience Platforms (DXP) MetrixPlus MetrixPlus Corporate Performance Management (CPM) Software OrgPlus OrgPlus Org Chart Software Palmira Professional Services on KNIME Software Palmira Professional Services on KNIME Software Data Science & Machine Learning Platforms SyncPlus SyncPlus Requirements Management Software webMethods webMethods Cloud Integration Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=LvEoemAAAAAJ&hl=ko&oe=ASCII | Yuqi Jia - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 전체 2021년 이후 서지정보 456 456 h-index 6 6 i10-index 6 6 0 400 200 100 300 2022 2023 2024 2025 2026 2 2 47 386 16 공개 액세스 모두 보기 모두 보기 자료 3개 자료 0개 공개 비공개 재정 지원 요구사항 기준 공동 저자 Neil Zhenqiang Gong Associate Professor, Duke University duke.edu의 이메일 확인됨 Yupei Liu Penn State psu.edu의 이메일 확인됨 Jinyuan Jia Assistant Professor, Penn State psu.edu의 이메일 확인됨 Dawn Song Professor of Computer Science, UC Berkeley cs.berkeley.edu의 이메일 확인됨 Minghong Fang University of Louisville louisville.edu의 이메일 확인됨 Yiran Chen John Cocke Distinguished Professor of Electrical and Computer Engineering, Duke University duke.edu의 이메일 확인됨 Saeed Vahidian University of California, San Diego (UCSD), Duke University ucsd.edu의 이메일 확인됨 Jingwei Sun Assistant Professor of CISE, University of Florida ufl.edu의 이메일 확인됨 Jianyi Zhang Research Scientist@Google Deepmind, PI@Duke University duke.edu의 이메일 확인됨 Hongbin Liu Google Deepmind google.com의 이메일 확인됨 Junchi Yan Fellow of IAPR & ICML Board Member, SJTU (2018-), AWS (2019-22), IBM (2011-18) cs.sjtu.edu.cn의 이메일 확인됨 팔로우 Yuqi Jia Duke University duke.edu의 이메일 확인됨 - 홈페이지 AI Security 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Formalizing and benchmarking prompt injection attacks and defenses Y Liu, Y Jia, R Geng, J Jia, NZ Gong 33rd USENIX Security Symposium (USENIX Security 24), 1831-1847 , 2024 333 2024 DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks Y Liu, Y Jia, J Jia, D Song, NZ Gong 2025 IEEE Symposium on Security and Privacy (SP), 2190-2208 , 2025 40 2025 Promptarmor: Simple yet effective prompt injection defenses T Shi, K Zhu, Z Wang, Y Jia, W Cai, W Liang, H Wang, H Alzahrani, J Lu, ... arXiv preprint arXiv:2507.15219 , 2025 24 2025 Unlocking the potential of federated learning: The symphony of dataset distillation via deep generative latents Y Jia, S Vahidian, J Sun, J Zhang, V Kungurtsev, NZ Gong, Y Chen The European Conference on Computer Vision (ECCV) 2024 , 2023 15 2023 A Critical Evaluation of Defenses against Prompt Injection Attacks Y Jia, Z Shao, Y Liu, J Jia, D Song, NZ Gong arXiv preprint arXiv:2505.18333 , 2025 13 2025 Evaluating {LLM-based} Personal Information Extraction and Countermeasures Y Liu, Y Jia, J Jia, NZ Gong 34th USENIX Security Symposium (USENIX Security 25), 1669-1688 , 2025 12 * 2025 Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning Y Jia, M Fang, H Liu, J Zhang, NZ Gong Conference on Neural Information Processing Systems (NeurIPS) 2025 , 2024 5 2024 Promptlocate: Localizing prompt injection attacks Y Jia, Y Liu, Z Shao, J Jia, N Gong 2026 IEEE Symposium on Security and Privacy (SP) , 2025 4 2025 Kissat adaptive restart, kissat cfexp: Adaptive restart policy and variable scoring improvement Y Li, Y Jia, W Luo, HL Zhen, X Li, M Yuan, J Yan SAT COMPETITION 2022, 39 , 2022 4 2022 Secinfer: Preventing prompt injection via inference-time scaling Y Liu, Y Wang, Y Jia, J Jia, NZ Gong arXiv preprint arXiv:2509.24967 , 2025 3 2025 Competitive advantage attacks to decentralized federated learning Y Jia, M Fang, NZ Gong Conference on Neural Information Processing Systems (NeurIPS) 2025 , 2023 2 2023 WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents Y Liu, R Xu, X Wang, Y Jia, NZ Gong arXiv preprint arXiv:2510.01354 , 2025 1 2025 ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data R Wang, Y Jia, NZ Gong Network and Distributed System Security (NDSS) Symposium 2026 , 2025 2025 Periodic Recovery from Poisoning Attacks in Machine Learning Y Hu, M Fang, Y Jia, H Liu, NZ Gong IEEE Transactions on Dependable and Secure Computing , 2025 2025 FoundationForensics: Traceback Backdoor Attacks for Vision Foundation Models H Liu, Z Shao, Y Jia, J Zhang, M Fang, C Hong, NZ Gong The SAT Encoding for Graph Isomorphism Y Li, Y Jia, W Luo, H Zhen, X Li, M Yuan, J Yan SAT COMPETITION 2022, 85 , 0 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–16 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://uk.linkedin.com/company/320mediamatthewhussey | Matthew Hussey / 320 Media | LinkedIn Skip to main content LinkedIn Articles People Learning Jobs Games Sign in Join for free Matthew Hussey / 320 Media Media Production The world’s leading advice for dating and confidence. Follow View all 15 employees Report this company About us Matthew Hussey is a New York Times bestselling author, owner of 320 Media, and coach specializing in confidence and relational intelligence. His YouTube channel is number one in the world for love life advice, with over half a billion views. He writes a weekly newsletter and is the host of the podcast Love Life With Matthew Hussey. Matthew provides monthly coaching to the members of his private community at LoveLifeClub.com. Over the past fifteen years, his proven approach has inspired millions through authentic, insightful, and practical advice that not only enables them to find love but also feel confident and in control of their own happiness. Learn more about Matthew Hussey and 320 Media at MatthewHussey.com Website LoveLifeBook.com External link for Matthew Hussey / 320 Media Industry Media Production Company size 11-50 employees Headquarters London Type Privately Held Locations 43 BERKELEY SQ London, W1J 5AP, GB Get directions Employees at Matthew Hussey / 320 Media Matthew Hussey Daniel Hyde DAVID KIRK Lauren McNeill See all employees Updates Matthew Hussey / 320 Media reposted this Celia Bradfield 1mo Report this post Matthew Hussey / 320 Media is looking for a Social Media Moderator & Editor to join our team on a short term contract this January 🔥 If you have experience editing short form videos, creating posters using Canva templates and connecting with real people to guide them towards the help they need, we'd love to hear from you👇 Check out the ad below for details on how to apply. Social Media Moderator & Editor Matthew Hussey / 320 Media, United Kingdom 8 4 Comments Like Comment Share Matthew Hussey / 320 Media reposted this Matthew Hussey 1mo Report this post New York City just ranked as the 5th WORST city to find love . . . and if you live there, you probably aren’t surprised. Some people blame the sheer density of people, which has led to an epidemic of commitment-phobes and endless situationships. Dating apps seem to be broken there too. NYC also ranked as the worst in a survey rating honesty (about things such as a person’s age, job, and appearance) among online daters. But it doesn’t have to be this way. For years, so many of my viewers have asked me to create a dating app, and for everyone in NYC who feels like they’ve tried everything and nothing works, I’ve done one even better. Introducing Sync. Sync isn’t just another dating app. It’s an AI-powered matchmaker designed to help you find real, meaningful connections by getting to know who you truly are and introducing you to people you’re deeply compatible with. No endless swiping, no wasted time . . . just real connections and better dates. We’re launching a beta test in NYC, so if you live there, this is your chance to experience something truly different. You can join the waitlist and be the first to try it out by going to http://TalkToSync.com now. 30 8 Comments Like Comment Share Matthew Hussey / 320 Media 1,165 followers 10mo Report this post We're #hiring a new Technical Operations Administrator in United States. Apply today or share this post with your network. Technical Operations Administrator Matthew Hussey / 320 Media, United States Like Comment Share Matthew Hussey / 320 Media 1,165 followers 11mo Report this post We're #hiring a new Digital Marketing Manager in Florida. Apply today or share this post with your network. Digital Marketing Manager Matthew Hussey / 320 Media, Florida, United States 3 Like Comment Share Matthew Hussey / 320 Media 1,165 followers 11mo Report this post We're #hiring a new Technical Operations Administrator in United States. Apply today or share this post with your network. Technical Operations Administrator Matthew Hussey / 320 Media, United States 3 Like Comment Share Join now to see what you are missing Find people you know at Matthew Hussey / 320 Media Browse recommended jobs for you View all updates, news, and articles Join now Similar pages The Matthew Hussey Company Online Audio and Video Media 320 Media Media Production Los Angeles, California Sarum Private Office Professional Services PX3 Partners Venture Capital and Private Equity Principals Four Candles Productions Ltd Online Audio and Video Media The Hyde Gallery Retail Art Dealers How to Get the Guy Online Audio and Video Media AVATR Egypt Retail Motor Vehicles Qesm 1st 6 October, Al Jizah Gumball Advertising Services Los Angeles, California Esther Perel Mental Health Care New York, New York Show more similar pages Show fewer similar pages Browse jobs Developer jobs 33,470 open jobs Wordpress Developer jobs 2,113 open jobs Marketing Specialist jobs 7,844 open jobs Engineer jobs 79,088 open jobs Writer jobs 3,391 open jobs Web Development Manager jobs 1,857 open jobs Website Manager jobs 1,940 open jobs Advertising Specialist jobs 1,257 open jobs Content Manager jobs 8,452 open jobs Business Development Specialist jobs 8,972 open jobs User Experience Designer jobs 2,027 open jobs Show more jobs like this Show fewer jobs like this More searches More searches Developer jobs Business Development Executive jobs Sales Manager jobs Account Manager jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Matthew Hussey / 320 Media Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/south-system-produtos-digitais/#main-content | DIGITAL PRODUCTS | LinkedIn Skip to main content LinkedIn SOUTH SYSTEM in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in DIGITAL PRODUCTS Strategic Planning Software by SOUTH SYSTEM See who's skilled in this Add as skill Contact us Report this product About We are always updating information that occurs in the digital world in order to understand our economic market and create new ideas. Our digital world is volatile, we know of the difficulty in creating an expectation of linear progress towards the construction of new products. Volatility creates a lot of uncertainty for decision-making, we cannot predict what will work, new startups and new ideas for products and services are emerging every day. The digital transformation is complex, involving people, culture, technologies, competitors, innovation, processes, and business. Through the vision and understanding of the market, we can develop simple solutions with a focus on what is really important for the business. In addition to the flexibility of adaptations, we have created a consistent culture that allows us to have business agility. Media Products media viewer No more previous content Desenvolvimento Produtos Digitais ão importante quanto o produto final, um processo de construção fluido e integrado é fundamental para garantir a excelência de produtos digitais. Nosso time desenvolve produtos com escopo aberto a partir da metodologia Dual-Track-Agile, em que o cliente pode optar por um ciclo parcial – com Design Sprint e Discovery – ou completo, acrescentando a etapa Delivery. Design Sprint O Design Sprint é uma das práticas que realizamos com nossos clientes, desta forma podemos criar produtos e/ou serviços inovadores com alto índice de assertividade para o seu negócio. DTA - Dual Track Agile Construímos produtos digitais junto com nossos clientes, pois assim poderemos identificar suas necessidades, entrevistar usuários, pegar feedbacks, realizar pesquisas, desenvolver protótipos, validar e testar novas ideias antes mesmo de iniciarmos o desenvolvimento. Desta forma, reduzimos riscos e evitamos investimentos astronômicos. Em outras palavras, estamos falando de cultura de produto e melhoria contínua. No more next content Featured customers of DIGITAL PRODUCTS Sicredi Financial Services 1,750,677 followers B2B.reservas IT Services and IT Consulting 5,857 followers Quanta Previdência Non-profit Organizations 15,436 followers PAYER Financial Services 727 followers Getnet Brasil IT Services and IT Consulting 325,683 followers UNICRED Financial Services 210,600 followers Thummi Global Hospitals and Health Care 1,754 followers Show more Show less Similar products Focus Focus Strategic Planning Software Aha! Roadmaps Aha! Roadmaps Strategic Planning Software Cascade Cascade Strategic Planning Software WorkBoard WorkBoard Strategic Planning Software Stratsys platform for compliance and efficiency Stratsys platform for compliance and efficiency Strategic Planning Software Dataport Consulting Dataport Consulting Strategic Planning Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/categories/software-development-kits | Best Software Development Kits (SDK) | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Software Engineer (58) Developer (25) Senior Software Engineer (23) Product Manager (19) Application Developer (17) See all products Find top products in Software Development Kits (SDK) category Software used to create platform-specific applications, such as those for iOS or the .NET framework. - Utilize integrated compilers and debugger tools - Incorporate additional features and functions such advertising and push notifications - Perform analysis of application activity 299 results Meta Business SDK Software Development Kits (SDK) by Meta The Meta Business SDK gives you access to our suite of business APIs allowing you to build unique and customized solutions to serve your businesses and clients. View product MantHANA Software Development Kits (SDK) by Bosch Global Software Technologies MantHANA is Bosch’s Rapid Deployment Kit that drives hardware and technology changes during S/4 HANA implementation. By integrating country-specific expertise and SAP best practices acquired by Bosch over the years it helps accelerate the S/4 HANA journey for a successful digital transformation. The Methodology for S/4 HANA Transition • Ready process lists speeds up Requirements Analysis • Business process blueprints included for complex processes • Predefined concepts to enable early-stage activity • Detailed cutover plan to ensure ease of S/4HANA transition View product Tencent Effect SDK Software Development Kits (SDK) by Tencent Tencent Effect SDK leverages YouTu's accurate AI capabilities and Pitu's rich real-time effects to offer a wealth of services for many video processing use cases. View product Elevate Software Development Kits (SDK) by Accedo.tv Ready-to-go OTT apps with unlimited customization opportunities. Elevate condenses Accedo’s vast experience in OTT UX strategy, design, and engineering into an easy-to-deploy application framework. A solution combining the quick time to market of ready-made OTT applications with all the customization benefits of bespoke video services - the best of both worlds. View product Lyzr AI Software Development Kits (SDK) by Lyzr AI Lyzr is a low-code agent framework with an agentic approach to building generative AI applications. Its fully integrated agents come with pre-built RAG pipelines, allowing you to build and launch in minutes. With Lyzr, you can build chatbots, knowledge search, data analysis, RAG-powered apps, and multi-agent workflow automation with minimal effort. The best part is that you can get locally deployable SDKs and private APIs to run the agents on your cloud, thus eliminating all concerns related to data privacy, compliance, and latency. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights RevenueCat Software Development Kits (SDK) by RevenueCat RevenueCat gets engineers back to adding differentiating value to your apps, rather than spend their time on never-ending maintenance of subscription plumbing. Through SDKs for all mobile frameworks, support for all app stores and web, a flexible API, and native integrations with all your marketing, CRM, and other tooling, RevenueCat ensures that your customers can purchase from your across platforms, while your Product, Marketing, Growth and CRM teams can trust that the data that feeds into their tooling is clean, reliable, and accurate. View product Ready Player Me Software Development Kits (SDK) by Ready Player Me Ready Player Me provides developers with easy-to-integrate Avatar Creator and developer tools to give their users highly personalized characters to help increase retention and engagement. View product Quest Software Development Kits (SDK) by LISNR Easily create gamified customer engagement experiences with the Quest platform. Quest’s data ingestion engine goes beyond traditional loyalty to help brands incentivize the most impactful customer actions. With Quest, you’ll grow your business through repeat customers and new revenue streams, not by discounting your brand. View product Radius Software Development Kits (SDK) by LISNR One-to-many long-range ultrasonic data transfer (SDK) between devices greater than 10ft. Optimized for long-range control/reliability of data transmission. View product Dante Software Development Kits (SDK) by Audinate Dante replaces point-to-point audio & video connections with easy-to-use, scalable, flexible networking. Adopted by hundreds of manufacturers in thousands of products, Dante is the de facto standard for modern AV connectivity. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/posts/digitaleconomycouncil_29-january-2026-live-webinar-we-are-pleased-activity-7415162648016916480-k_Ik | 29 January 2026 | Live Webinar We are pleased to support an upcoming investigative webinar from Chainalysis. Investigate Live with Chainalysis: Inside a Billion-Dollar Cocaine Empire. Once an… | Digital Economy Council of Australia (DECA) Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join for free Digital Economy Council of Australia (DECA)’s Post Digital Economy Council of Australia (DECA) 16,292 followers 4d Report this post 29 January 2026 | Live Webinar We are pleased to support an upcoming investigative webinar from Chainalysis . Investigate Live with Chainalysis: Inside a Billion-Dollar Cocaine Empire. Once an Olympian-caliber snowboarder, Ryan Wedding is now alleged to be one of the most significant cocaine traffickers operating across Colombia, Mexico, the United States, and Canada. This session provides a rare, practical look at how blockchain intelligence is used in real investigations, including wallet analysis, stablecoin flows, and laundering typologies linked to narcotics trafficking. Event details 🗓 29 January 2026 ⏰ 2pm AEDT 📍 Live webinar Register: https://bit.ly/49argpv 7 Like Comment Share Copy LinkedIn Facebook X To view or add a comment, sign in 16,292 followers View Profile Connect Explore content categories Career Productivity Finance Soft Skills & Emotional Intelligence Project Management Education Technology Leadership Ecommerce User Experience Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Sign in to view more content Create your free account or sign in to continue your search Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#introduction | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
https://huggingface.co/datasets/MLCommons/peoples_speech | MLCommons/peoples_speech · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: MLCommons / peoples_speech like 246 Follow MLCommons 97 Tasks: Automatic Speech Recognition Modalities: Audio Text Formats: parquet Languages: English Size: 1M - 10M ArXiv: arxiv: 2111.09344 Tags: robust-speech-recognition noisy-speech-recognition speech-recognition Libraries: Datasets Dask Polars + 1 License: cc-by-2.0 cc-by-2.5 cc-by-3.0 + 3 Dataset card Data Studio Files Files and versions xet Community 28 Dataset Viewer Auto-converted to Parquet API Embed Duplicate Data Studio Subset (7) clean · 1.55M rows clean (1.55M rows) clean_sa (311k rows) dirty (5.53M rows) dirty_sa (602k rows) microset (336 rows) test (34.9k rows) validation (18.6k rows) Split (3) train · 1.5M rows train (1.5M rows) validation (18.6k rows) test (34.9k rows) SQL Console id string lengths 44 176 audio audio duration (s) 1.02 15 duration_ms int32 1.02k 15k text string lengths 5 377 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00000.flac 14,920 i wanted this to share a few things but i'm going to not share as much as i wanted to share because we are starting late i'd like to get this thing going so we all get home at a decent hour this this election is very important to 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00001.flac 14,530 state we support agriculture to the tune of point four percent no way i made a mistake this year they lowered it from point four percent to point three eight percent and in the same breath they're saying food 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00002.flac 14,790 security so it doesn't feel very secure to me as a farmer to hear that and my family and i we've been farming here since nineteen ninety 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00003.flac 14,830 three and we produce last year we produce twenty one thousand pounds of food for the community on two thousand square feet so unless we were that efficient to produce that much food 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00004.flac 14,940 commons here in the spirit of being able to grow our food here locally so we started as an organization in actually in two thousand and nine but really in two thousand and ten march of two thousand and ten we had our first meeting 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00005.flac 14,340 on maui and now we have ten chapters across the islands and about nine hundred members so we are growing exponentially and we're fortunate to know that we have not only 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00006.flac 14,920 farmers but gardeners and foodies alike who value our mission and what we're what we're about in rejuvenating our lands and also at the same time advocating for our local food production so what we've done as an 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00007.flac 14,620 organisation is put together a five point plan you'll hear about that five point plan tonight in our questions and that five point plan basically deals with the whole system of agriculture what makes up the whole system of agriculture and as we see it is 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00008.flac 14,970 at forty years old getting into farming didn't know what i was doing i was a gardener you know but i had the passion and that's what i still have today and that's what's can sustain our family farm along with my wife's passion and our son who works full time on the farm and our 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00009.flac 14,830 daughter who came out of it actually she designs and fabricate her own women's swimwear line so here she grew up in a farm family knew about being an entrepreneur and she went and got to go work for somebody else you know and design 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00010.flac 14,980 has her own business in that respect so there's a lot of benefits to our economy that represents a family farm the multiplier effect we like to call it so outside of work workforce development we support agricultural land trust we 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00011.flac 14,770 get out once they get it and that would be enforced in a way that we wouldn't have any quote unquote gentleman estates they would be active farms and so we have a man in our organization who's actually a board member of our five hundred one c three foundation tailbone our has been 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00012.flac 14,820 advocating advocating and working on developing that third thing is new treat recycling centers we're developing and advocating for those in our regions c the reason why we have so many chapters is because we want to 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00013.flac 14,800 build our agricultural strength regionally we want to you know when you're growing things in hama it's a lot different than you're growing in line where james is right now you know and so each region has its own issues and its own challenges and its own benefits 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00014.flac 14,740 and we want to highlight those and bring that to where we can have a supportive system in place so nutrient recycling our nutrients back on to the land to rejuvenate the soils that have been depleted by plantation agriculture over a long period of time 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00015.flac 14,500 is an important aspect of what we represent and the fourth thing is food hubs have aggregates places where we can as farmers bring all our produce and then have that aggregate out whether it's fresh and 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00016.flac 14,770 and it's so beautiful to see these kind of farms these boutique farms springing up all over the place so it's important that we support our farmers first and foremost making a living at what they love to do and secondly to put across 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00017.flac 14,860 five point plan and you the folks that are running for office they can get into office to support us in this respect because we're poised to work with anyone who is willing to work with us so on that note i'd like to introduce our first 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00018.flac 14,950 but domestic violence doesn't happen in a vacuum it's a lot of the community issues things like poverty homelessness housing all the different effects of of you know living on an island community and the cost of living and all those kinds 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00019.flac 14,920 i know on a very small scale what farmers experience on a large scale aside from the having to make a living at it so i'm not doing it on that level i'm just trying to raise enough tomatoes for my grandson 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00020.flac 14,920 to eat every morning so i am here mostly to learn to i'm glad to know that the white farmers union is relatively young and so i'm not too far behind the curve and i'm grateful to be 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00021.flac 14,650 development sorry for the false start on that and there are comment on that is that with the average age of farmers in hawaii it at sixty we can all agree we need to grow a new generation of farmers equipped with the skills to create successful farming 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00022.flac 14,950 also having gotten grants from the county i know that they have a lot of requirements but i think when you're looking at a program like this you're looking at something new and something different so i think everyone could come with a different set of 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00023.flac 14,640 goals and they might all be very very worthy right because you might have somebody who's trying to create a farm you might have somebody who are who has a farm was trying to get a bigger farm you might have somebody with a big farm that's trying to invest in and infrastructure more 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00024.flac 14,490 equipment or something like that so i think those kinds of grants shouldn't be too restrictive because you need to be able to be creative with new projects so i would support that because i think the need is here and it's huge 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00025.flac 14,800 question and the statement and i think of the programs that we have in place programs that we grew up with like f if a and things like that i noticed as an adult i don't see as much participation when we were in 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00026.flac 14,860 much anymore and that's something that we need to start to support more in our schools to support our fund i'd like to see that apprenticeship programs incorporate alternative farming practices i 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00027.flac 14,920 you would want a beginning farmer program to have in order to win your support absolutely absolutely in my thoughts in a farm apprenticeship program in any apprenticeship program is importance of diversity in their training as a young farmer 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00028.flac 14,890 diversity in pest control in soil maintenance which is a big issue that will be discussing in a little bit and especially i think a lot of people when they think about farm apprenticeships they think about manual labor so i that's why i would like to see more training and 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00029.flac 9,661 more education in the program so that the farmers that we produce are going to be able to accept and be able to deal with some of the change in diversity in the market thank 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00030.flac 14,851 thank you all our next question is strangely enough on the same theme only it's about nutrient cycling centers and soil health and regenerative agriculture so our lead in comment currently many of our hawaii 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00031.flac 14,860 farmers months purchased imported nutrient farm amendments is an expense for farmers that's passed down to the consumer in the meantime we accept twenty thousand tons of food waste at the maui county dump that could 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00032.flac 14,400 one of the barriers is definitely that many of our leaders are not maybe not privy to the background of all the different farming 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00033.flac 14,950 practices in the last two years of my degree i focused on the anthropology of agriculture and how different countries throughout the world are now reverting back to their indigenous agriculture systems in brazil 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00034.flac 14,860 in korea and learning that the system that worked all along was the best system for the place which makes perfect sense but we've been i think in a in a place where we've 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00035.flac 14,920 we have multiple hotels here who do these huge catering jobs and have all this extra food and i actually know that because sometimes the food ends about our shelter when it's good but you know there's all this byproduct you know when you're prepping food 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00036.flac 14,590 all that stuff there's so much food just from the hotels and catering companies that could end up in composting that makes perfect sense to me i think part of the problem and the barrier is that we similar 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00037.flac 14,610 we don't know better yet like we're just learning about that that we could take all that food and turn it into wonderful rich soil is it's not a new concept by any means is a very old concept but we've gotten used to doing 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00038.flac 14,980 educate us as county council and as leaders throughout the state about the importance of that thank you thank you very much all of you thank you i don't know if we mention this this race actually has four people running but we 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00039.flac 14,970 we need an empty seat ok food helps across the nation food hubs are becoming solutions for centralizing food processing and distribution increasing food production capabilities for small farmers by paving the way for 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00040.flac 14,920 cooperatives our five point plan is working with the state wide farm to school initiative for growing food for the dio we school lunch program all three of you you have one minute please describe benefits you can imagine 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00041.flac 14,260 for the citizens of maui that would result from the maui county facilitating in funding a food hub let me repeat that please describe benefits you can imagine for the citizens of maui that would result from maui county 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00042.flac 14,860 fishermen up there selling for fresh fish you've got people growing and cooking with their own food and and selling wonderful fresh food at the market so something like that i i also think that oh and one of the biggest things that 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00043.flac 14,590 happened for my family is this fresh eggs you know getting our gannett eggs that cost goes great by getting locally grown eggs that are all different sizes and colors and and when there's a huge difference so that was an 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00044.flac 14,830 education for me and you know one of my things that i'm i keep saying is you know i grew up in a time where things were different and going to the supermarket became a luxury and that if you had any status you go to the market you don't have to have your own chickens but we're reclaiming that now and i think 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00045.flac 14,920 and what happened people grew their own food people worked on barter systems people were able to have their own food hubs in their communities where they were able to trade and barter their goods for the things they needed why do i think food hubs are important because a food hub for sustainable 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00046.flac 14,490 training that would be involved with that education for these people this is part of the five point plan for the farmers union in my mind to bring apart this new change in our agricultural system and how we view our food how what we eat and how we eat it so i would be completely 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00047.flac 14,890 for developing these food hubs for the idea of training apprenticeship programs bringing healthy food into our community and developing through the county of maui ways that we can use and certify these are getting farms so that a food can be given 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00048.flac 15,000 so we're going to switch to policy a little bit and we're going to have a separate question for each of you we have specific questions with each of you in mind our topic is the farm land zoning and affordable land trusts in other words 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00049.flac 14,590 this you have two minutes so here's your question our organization supports the concepts of farmers living on the land they farm and lease through an agricultural land trust what 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00050.flac 14,800 ideas would you propose in moving in this direction so that it would be actualized in other words how can we make it so that people can lease farm lands and actually live on them it's a wonderful question it's interesting thing is i think we're looking at 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00051.flac 14,740 housing start developing more sustainable lands that these farmers are actually putting more interest into their land as they're developing the cost and the resources that they can be gained from that as we're developing that we need to look i think we need to look at that 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00052.flac 14,970 community is to start getting on some big business to say what is your plan especially alexander bald how are you planning on developing this for as you they have stated for use for individual farmland once that is together then i think we can move forward as a group towards a project to 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00053.flac 14,710 speaking with right now so these are three of the four candidates for the a country consul seat a stacey you have your own question two minutes what are your ideas for changing eggs zoning that will allow for more options for farm 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00054.flac 13,450 worker dwellings including temporary structures such as the new trend of tiny houses in your i think that's an excellent idea i love the title house idea and i think that we do need to change some of our 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00055.flac 14,860 regulations if you will to allow for that because right now it's kind of complicated you really can't just put up a year you still need a permit if you have a tidy house you need to put it on wheels i mean it's kind of silly but i think that as a county if 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00056.flac 14,820 we're really committed to one affordable housing which we keep saying we are and if we are really committed to farming and growing our food and supporting local businesses these are all very small businesses we're trying to support we keep saying we 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00057.flac 14,830 are and we need to find ways to make that happen and so i would support that i think the concern is that sometimes people will say that it's workforce housing and build a mansion on their land so i think that we would 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00058.flac 14,890 want to monitor that and have an enforcement part of this as well to make sure it's one thing yes we absolutely want to support workforce housing if you're working on the farm that's very important and we all have to have support and housing 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00059.flac 14,890 you know looking at not everybody's paying their fair share sometimes on taxes some people are paying too much some people are not paying enough so to have an a foresman piece to make sure everybody's paying their fair share that's really important to me i think we need to look at that and that that would actually pay for itself 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00060.flac 14,790 pretty quickly i also wanted to say that you know the we have a big housing crisis here so this is a solution i think to several problems 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00061.flac 7,450 the housing and the ag and the growing food so i think it's a good solutions i'm really glad you're asking those questions thank you 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00062.flac 14,920 thank you have two minutes and your question is completely different given what it costs for the average farmer to rent a house lease farmland pay for equipment pay for imported amendments and import irrigation costs etc in other words 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00063.flac 14,830 there's a lot of cost if you want to farm what do you think it will take to make farming more successful enterprise and what could you do about it if you're elected i think it is going to take the corporation 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00064.flac 15,000 of county and state government to be able to put aside those funds you know in just touching on the other questions i think i believe in order for us to change what 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00065.flac 14,710 is acceptable and that's going to take a change to what you revert by statutes or change to our county charter but that's something as policymakers that is in our power to do and i think we need to be able to look at the 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00066.flac 14,860 policies that have been in place for ever and and reexamine if they truly suit us today and if they don't then we need to look at what our community really needs and funding i would be able to bring different 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00067.flac 14,860 parts of our community together i think one of my strengths is being able to reach out to those who are the experts in their field i readily know that i am not in experts in off field and i am aware 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00068.flac 15,000 of that and i i very much honor and respect the expertise of those people who are experts when i was on the state land use commission i did vote against of very controversial development on awful because 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00069.flac 14,800 how much the cost of irrigation would be to develop a new site and so as policy makers as government leaders we need to be able to protect those people who are producing food we need to be able to protect those 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00070.flac 14,890 places that they are currently farming those places that are currently in ag and we need to to put aside those funds and invest if security food sustainability is our goal like water 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00071.flac 9,840 infrastructure like all those things like like housing affordable housing we need to be able to prioritize and give funding to those places thank you so much 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00072.flac 14,320 third party a completely one of the thoughts that i've had is maybe it should be a separate entity that just doing the public trust maybe not necessarily a nonprofit but it could be a nonprofit but it could be a completely separate 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00073.flac 14,950 corporation that runs and maintains that system because right now the the challenge is you know we have a big corporation who has used that water system for its very existence and sugar you know 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00074.flac 14,820 so and they you know they built it and they've maintained it but they've also read their investment many times over so now it's time to share the water with everyone re stores some of the streams that have 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00075.flac 14,980 been you know they've cut the streams off so the life cycles there have completely changed and there are farmers along the way we need to if our commitment is to diversify agriculture we're going to need to share that water 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00076.flac 14,020 invested interests in it owning it maybe it's the state i mean maybe that's the best answer maybe it's a third party i i would like to investigate that more thank you very much 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00077.flac 14,940 system that needs repair and or replacement how do you as a candidate see the needed infrastructure being put in while dealing with the multiple entities out there that wish to control the water should i repeat that 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00078.flac 14,740 was the legislature approved alexander bottom to keep the water rights for the next thirteen years that's a complete travesty that should have that should be immediately really looked at and changed so that we're not it's not under corporate control i believe all of that water and that infrastructure that was built 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00079.flac 14,830 supplies water to the plantation not counting your game and there was water by is everywhere i think we need to get control back of our water system so we can use it to get back to the streams to get back to our the people who need it with that we need to deal with our water quality 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00080.flac 14,670 we have to get back to looking at the old system you know we have great groups at the watershed partnerships we have to make sure that the water coming from the mountain is safe healthy and clean for our farmers to use i think we need to look at it as this top down system 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00081.flac 10,630 protect our water resources and again to reclaim the water that's here on the island to the people who really deserve it and not the large corporations who abused it thank you thank you 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00082.flac 14,530 there and not in use and it's it's shameful it's disgraceful when so many people need it that we hear so often about the need of all the different parts of our community that no one entity should be able to 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00083.flac 9,240 waste that way and so i would be very active in looking at the policies that concern this thank you very much 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00084.flac 14,590 economic efficiency with the hope that this would replace currently employed practices that the farmers union doesn't really support so knowing that we have a few questions for you starting with eric 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00085.flac 14,650 what would you do to empower the hawaii department of agriculture in hawaii health department by supporting bills that monitor pesticide drift to protect our health and environment such as things like product testing soil 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00086.flac 14,940 citizens in maui county need to take the helm on that and start doing their own tests there are organizations the department of water supply there's other groups where you can swab your screens i think we need to find out especially if you're living next to an agricultural area where there is spring or you 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00087.flac 14,800 suspect to look at what the chemicals are in the area with that i have to say that i think a lot of it is up to the individual landowner i'm against pesticides you know in my in my career and i have a large stand as a farmer 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00088.flac 14,680 stacey one minute again when it's been proven that there are biological applications that can provide solutions to agricultural production issues what is your position on promoting these over practices that 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00089.flac 14,860 use other substances which which are well known hormonal disruptors and possible carcinogens and might cause physical harm to both people and the environment so the question is about 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00090.flac 14,590 if there are proven biological applications what your position on promoting the over you know our business as usual practices again i think it comes back to when you know better and i have to do better so 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00091.flac 14,980 part of the i sat on the resolutions committee for the democratic party last year or last convention two years ago and one of the big things that came up from koichi was that people children were being born with horrible birth defects you couldn't deny it 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00092.flac 15,000 there was such a high level of that that was proving to be connected to pesticides and runoff and things like that and so the party created a position saying that that need to stop that we need to be informed and that people need to know what 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00093.flac 14,860 was happening in their areas because it was so dramatic i would absolutely support that too i think the least that we can expect is to know what's going on in our especially near schools and there are homes near parks and if there are 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00094.flac 14,830 biological ways that will work then we need to look at that if we if there are proven ways then we need to use that instead because i know that there are ways that are we're just not using because we're not being sort of sold by dow chemical you know 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00095.flac 14,920 parks and our our highways our department of parks and rec our our county managing director if we can be able to show through experience through through it works that these these alternative 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00096.flac 14,950 methods and methods that are better for us where then then they're more apt to use them and i would want to create policies to make us use them thank you thank you very much we have one last 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00097.flac 14,460 you one last question and this one's labeled other but it's for all three of you and we'll give you one minute we have noticed that many of the candidates running this year are freshman in a field of potentially seasoned council 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00098.flac 13,540 potentially seasoned council members how do you see working together with others that may not share your values or point of view in how to address our agricultural needs and eric you can go first one minute 07282016HFUUforum_SLASH_07-28-2016_HFUUforum_DOT_mp3_00099.flac 14,910 issues and be involved in any kind of negotiations and any kind of a planning there is always a need for mediation because there are always conflicting views as council member my goal would be to be there as that mediator to help bring End of preview. Expand in Data Studio Previous 1 2 3 ... 15,013 Next Dataset Structure Data Instances Data Fields Data Splits Dataset Creation Curation Rationale Source Data Annotations Personal and Sensitive Information Considerations for Using the Data Social Impact of Dataset Discussion of Biases Other Known Limitations Additional Information Dataset Curators Licensing Information Citation Information Dataset Card for People's Speech Dataset Summary The People's Speech Dataset is among the world's largest English speech recognition corpus today that is licensed for academic and commercial usage under CC-BY-SA and CC-BY 4.0. It includes 30,000+ hours of transcribed speech in English languages with a diverse set of speakers. This open dataset is large enough to train speech-to-text systems and crucially is available with a permissive license. Supported Tasks and Leaderboards [Needs More Information] Languages English Dataset Structure Data Instances { "id": "gov_DOT_uscourts_DOT_scotus_DOT_19-161/gov_DOT_uscourts_DOT_scotus_DOT_19-161_DOT_2020-03-02_DOT_mp3_00002.flac", "audio": { "path": "gov_DOT_uscourts_DOT_scotus_DOT_19-161/gov_DOT_uscourts_DOT_scotus_DOT_19-161_DOT_2020-03-02_DOT_mp3_00002.flac" "array": array([-6.10351562e-05, ...]), "sampling_rate": 16000 } "duration_ms": 14490, "text": "contends that the suspension clause requires a [...]" } Data Fields { "id": datasets.Value("string"), "audio": datasets.Audio(sampling_rate=16_000), "duration_ms": datasets.Value("int32"), "text": datasets.Value("string"), } Data Splits We provide the following configurations for the dataset: cc-by-clean ( "clean" ), cc-by-dirty ( "dirty" ), cc-by-sa-clean ( "clean_sa" ), cc-by-sa-dirty ( "dirty_sa" ), and microset ( "microset" ). We also provide validation and test configurations, which are not only available as standalone configurations but are also included as validation and test splits within each of the above configurations for ease of use. Specifically: Setting data_dir="validation" and split="validation" corresponds to the validation split of any of the configurations: "clean" , "clean_sa" , "dirty" , or "dirty_sa" . Similarly, setting data_dir="test" and split="test" corresponds to the test split of these configurations. ├── clean │ ├── train │ ├── validation │ └── test ├── clean_sa │ ├── train │ ├── validation │ └── test ├── dirty │ ├── train │ ├── validation │ └── test ├── dirty_sa │ ├── train │ ├── validation │ └── test ├── microset │ └── train ├── validation │ └── validation └── test └── test Dataset Creation Curation Rationale See our paper . Source Data Initial Data Collection and Normalization Data was downloaded via the archive.org API. No data inference was done. Who are the source language producers? [Needs More Information] Annotations Annotation process No manual annotation is done. We download only source audio with already existing transcripts. Who are the annotators? For the test and dev sets, we paid native American English speakers to do transcriptions. We do not know the identities of the transcriptionists for data in the training set. For the training set, we have noticed that some transcriptions are likely to be the output of automatic speech recognition systems. Personal and Sensitive Information Several of our sources are legal and government proceedings, spoken histories, speeches, and so on. Given that these were intended as public documents and licensed as such, it is natural that the involved individuals are aware of this. Considerations for Using the Data Social Impact of Dataset The dataset could be used for speech synthesis. However, this requires careful cleaning of the dataset, as background noise is not tolerable for speech synthesis. The dataset could be used for keyword spotting tasks as well. In particular, this is good use case for the non-English audio in the dataset. Our sincere hope is that the large breadth of sources our dataset incorporates reduces existing quality of service issues today, like speech recognition system’s poor understanding of non-native English accents. We cannot think of any unfair treatment that come from using this dataset at this time. Discussion of Biases Our data is downloaded from archive.org. As such, the data is biased towards whatever users decide to upload there. Almost all of our data is American accented English. Other Known Limitations As of version 1.0, a portion of data in the training, test, and dev sets is poorly aligned. Specifically, some words appear in the transcript, but not the audio, or some words appear in the audio, but not the transcript. We are working on it. Additional Information Dataset Curators [Needs More Information] Licensing Information We provide CC-BY and CC-BY-SA subsets of the dataset. Citation Information Please cite: @article{DBLP:journals/corr/abs-2111-09344, author = {Daniel Galvez and Greg Diamos and Juan Ciro and Juan Felipe Cer{\'{o}}n and Keith Achorn and Anjali Gopi and David Kanter and Maximilian Lam and Mark Mazumder and Vijay Janapa Reddi}, title = {The People's Speech: {A} Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage}, journal = {CoRR}, volume = {abs/2111.09344}, year = {2021}, url = {https://arxiv.org/abs/2111.09344}, eprinttype = {arXiv}, eprint = {2111.09344}, timestamp = {Mon, 22 Nov 2021 16:44:07 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-09344.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } Downloads last month 13,602 Use this dataset Homepage: mlcommons.org Repository: github.com Paper: arxiv.org Point of Contact: datasets@mlcommons.org Size of downloaded dataset files: 2.12 TB Size of the auto-converted Parquet files: 2.12 TB Number of rows: 8,051,212 Models trained or fine-tuned on MLCommons/peoples_speech nvidia/parakeet-ctc-1.1b Automatic Speech Recognition • 1B • Updated Sep 24, 2025 • 137k • 39 nvidia/canary-qwen-2.5b Automatic Speech Recognition • 3B • Updated 29 days ago • 64.1k • 346 nvidia/canary-1b-flash Automatic Speech Recognition • 0.8B • Updated Dec 3, 2025 • 56.4k • 264 nvidia/parakeet-rnnt-0.6b Automatic Speech Recognition • Updated Dec 3, 2025 • 5.35k • 12 nvidia/parakeet-tdt-1.1b Automatic Speech Recognition • Updated Dec 3, 2025 • 5.24k • 111 nvidia/parakeet-ctc-0.6b Automatic Speech Recognition • 0.6B • Updated Sep 25, 2025 • 4.05k • 23 Browse 41 models trained on this dataset Spaces using MLCommons/peoples_speech 2 👀 huggingfacejs/speech-recognition-vue 👀 arsalagrey/speech-recognition-vue Paper for MLCommons/peoples_speech The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage Paper • 2111.09344 • Published Nov 17, 2021 • 1 System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://huggingface.co/datasets/OpenDataArena/ODA-Mixture-500k | OpenDataArena/ODA-Mixture-500k · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: OpenDataArena / ODA-Mixture-500k like 116 Follow OpenDataArena 49 Modalities: Text Formats: parquet Size: 100K - 1M ArXiv: arxiv: 2512.14051 Libraries: Datasets Dask Polars + 1 License: apache-2.0 Dataset card Data Studio Files Files and versions xet Community = 10, then there is a carry. So, 2X + 1 >= 10 => X >= 4.5. Since X is an integer digit, X >= 5. So, if the digit before the trailing 9s is 5 or more, then adding that digit in n and n+1 will result in a carry.\n\nWait, that's an important point. So, when adding n and n+1, the only digit that can cause a carry is the digit that gets incremented when moving from n to n+1 (i.e., the first non-9 digit from the right). All other digits either add 9 + 0 = 9 (no carry) or the same digit in both numbers (if no trailing 9s). Wait, but if there are no trailing 9s, then n+1 is just n with the last digit incremented. For example, n = ABCD, n+1 = ABC(D+1). Then, adding n and n+1 would have the last digit as D + (D + 1) = 2D + 1. Similarly, the other digits are A + A, B + B, C + C. Wait, no: actually, n and n+1 differ only in the last digit if there are no trailing 9s. So, for example, n = 1234, n+1 = 1235. Then, adding them:\n\n1+1=2 (thousands), 2+2=4 (hundreds), 3+3=6 (tens), 4+5=9 (units). So, units digit is 4 + 5 = 9, others are same digits added together. Wait, no: wait, in n = 1234, the thousands digit is 1, hundreds 2, tens 3, units 4. In n+1 = 1235, thousands, hundreds, tens are the same, units is 5. So adding n and n+1:\n\nThousands: 1 + 1 = 2\nHundreds: 2 + 2 = 4\nTens: 3 + 3 = 6\nUnits: 4 + 5 = 9\nSo, all digits except the units are just double the original digits. But the units digit is 4 + 5 = 9. So, in this case, there's no carry. But if the units digit in n is 5, then n+1 has units digit 6, and adding them gives 5 + 6 = 11, which would carry over.\n\nWait, so in general, when adding n and n+1, the only digit that can cause a carry is the digit where the increment happens. If that digit in n is 5 or higher, then adding it to the next digit (which is one higher) will result in a carry. If the digit is 4 or lower, adding it to the next digit (which is one higher) won't cause a carry. For example:\n\n- If the units digit is 4: 4 + 5 = 9 (no carry)\n- If units digit is 5: 5 + 6 = 11 (carry)\n\nSimilarly, if the tens digit is being incremented (because the units digit was 9), then:\n\nn = ...X9, n+1 = ...(X+1)0. Adding them:\n\n...X9 + ...(X+1)0:\n\nDigits: For the tens place: X + (X + 1) = 2X + 1. If 2X + 1 >= 10, then carry. So, again, if X >= 5, carry occurs.\n\nSimilarly, if the hundreds digit is being incremented (because the tens and units were 99):\n\nn = ...Y99, n+1 = ...(Y+1)00. Adding them:\n\n...Y99 + ...(Y+1)00:\n\nHundreds place: Y + (Y + 1) = 2Y + 1. If 2Y + 1 >= 10, carry. So Y >= 5 causes a carry.\n\nSame for thousands place. For example, n = 1999, n+1 = 2000. Adding them:\n\n1 + 2 = 3 (thousands place)\n9 + 0 = 9 (hundreds)\n9 + 0 = 9 (tens)\n9 + 0 = 9 (units)\nNo carry, since 1 + 2 = 3 = 10, then a carry occurs. Therefore, even if the thousands digit A is 5, then 2A = 10, which would cause a carry. Wait, but A is the thousands digit. In our problem, A can be 1 or 2 (since the numbers are from 1000 to 2000). So, 2A would be 2 or 4, which are both less than 10. So, in our specific case, since the thousands digit is 1 or 2, 2A is 2 or 4, so no carry from the thousands place.\n\nBut wait, in the problem, we're adding numbers from 1000 to 2000. So, the thousands digit is 1 for all numbers except 2000, which has 2. So, when adding n and n+1, both numbers will have thousands digit 1, except when n = 1999 and n+1 = 2000. In that case, n = 1999 (thousands digit 1) and n+1 = 2000 (thousands digit 2). So adding those thousands digits: 1 + 2 = 3, which is less than 10, so no carry.\n\nTherefore, in our problem, the thousands digit addition will never cause a carry, because either 1 + 1 = 2 (for numbers from 1000 to 1998 and their consecutive pairs) or 1 + 2 = 3 (for the pair 1999 + 2000). So, the thousands place is safe.\n\nTherefore, the possible carries can only come from the hundreds, tens, or units places. Let's consider different scenarios based on where the increment occurs when moving from n to n+1.\n\nCase 1: The units digit is not 9. Then, n+1 is n with units digit incremented by 1. So, adding n and n+1, the units digits are D and D + 1. So, sum in units place: D + (D + 1) = 2D + 1. For there to be no carry, 2D + 1 D = 11, which causes a carry.\n\nBut wait, in our problem, if the units digit is not 9, then we increment the units digit. So, in this case, the only digit that changes is the units digit. Therefore, when adding n and n+1, the thousands, hundreds, and tens digits are the same in both numbers, so adding them would be 2A, 2B, 2C (which, as we saw, A is 1 or 2, so 2A is 2 or 4, which is safe; B and C can be 0-9, so 2B and 2C could be up to 18. Wait, hold on! Wait, if we are adding n and n+1 where only the units digit is changing, then actually, in the thousands, hundreds, and tens places, the digits in n and n+1 are the same. Therefore, when adding n and n+1, in the thousands place, it's A + A = 2A. Similarly for hundreds and tens places. So, for example, if n is 1234, then n+1 is 1235. Adding them:\n\nThousands: 1 + 1 = 2\n\nHundreds: 2 + 2 = 4\n\nTens: 3 + 3 = 6\n\nUnits: 4 + 5 = 9\n\nSo, all digits except units are doubled. Therefore, even if B or C is 5, then 2*5 = 10, which would cause a carry. Wait, that's a problem. Wait, in this case, even if the units digit is fine (e.g., D=4), but if another digit (like B or C) is 5 or more, then doubling it would result in 10 or more, hence a carry. But wait, the problem states \"no carrying required when the two integers are added\". So, even if a carry is caused by the hundreds or tens place, that pair is excluded.\n\nTherefore, my previous reasoning was incorrect. I had only considered the digit where the increment occurs, but actually, when adding n and n+1, all digit pairs are added, and if any of them (except the one that increments) sum to 10 or more, there's a carry. So, for example, if n has a hundreds digit of 5, then in n and n+1, the hundreds digits are both 5, so adding them gives 10, which is a carry. Therefore, such a pair would require carrying.\n\nWait, that complicates things. So, in order for the addition of n and n+1 to not require any carrying, all digit pairs (thousands, hundreds, tens, units) must sum to less than 10. But when adding n and n+1, since n+1 is formed by incrementing n by 1, the digits of n and n+1 can differ in more than one place if there are trailing 9s.\n\nWait, let me think again. For a number n, n+1 is formed by incrementing the last digit by 1, unless that digit is 9, in which case it rolls over to 0 and the next digit is incremented, and so on. Therefore, except for the digits that are rolled over from 9 to 0, all other digits remain the same. The first non-9 digit from the right is incremented by 1.\n\nTherefore, when adding n and n+1, the digits that are rolled over (from 9 to 0) will be added as 9 + 0 = 9 (no carry). The first non-9 digit from the right in n is incremented by 1 in n+1. All digits to the left of that remain the same. Therefore, when adding n and n+1:\n\n- For digits that were rolled over (i.e., trailing 9s in n): 9 + 0 = 9 (no carry)\n- For the first non-9 digit from the right in n: let's say it was D, then in n+1 it is D + 1. So, sum is D + (D + 1) = 2D + 1. If this is >=10, carry occurs.\n- For digits to the left of that: they are the same in n and n+1, so sum is 2*D. If 2*D >=10, carry occurs.\n\nTherefore, in order for the addition of n and n+1 to require no carrying, all the following must be true:\n\n1. For the digit where the increment occurs (the first non-9 digit from the right in n): 2D + 1 D =10)\n2. For all digits to the left of the incremented digit: 2*D D =10)\n3. For all digits that are rolled over (trailing 9s in n): 9 +0=9 which is okay.\n\nTherefore, in order for the addition n + (n+1) to not require carrying, the following must hold:\n\n- The first non-9 digit from the right in n must be D X Y Z X Y =10)\n- The hundreds digit X must be X P0: has 4 faces. Step1: adds 4 tetras. Step2: now, P1 has how many faces?\n\nEach original face (4) leads to???? Original faces: 4. Each being subdivided such? After adding tetrahedrons, new faces generated as.... In Pi+1, the number of faces is 16.\n\nBut actually, when adding a tetrahedron to a face:\n\nOriginal face: 1 triangle. Replace midpoint triangle with a tetra. So left withOriginal face split into three triangles. The added tetra has three new faces (the other sides).\n\nThus after step: for each face in Pi, Pi+1 face count is 3* (original face splits) plus 3*new faces.\n\nTherefore, the number of faces at each step Qi+1= 3*Qi + 3*Qi =6*Qi.\n\nWait, substituting that, for Pi's Q: If start with Q0=4, next Q1=6*4=24?\n\nWait maybe earlier Step1: start with four faces.\n\nEach face generates three faces from the original splits (the non-replaced parts) and three faces from the added tetrahedron, totaling 6 per face. Thus, Q1=4*6=24.\n\nThen Q2 would be Q1 multiplied by 6: 24*6=144. Similarly Q3=144*6=864. So Qi=4*6^i.\n\nBut the problem ends with P3, the volume up to third iteration.\n\nAlternatively, think in terms for the V. Volume at step0: Vi=1. Step1 added F0=4*V/8=0.5. So Vi+1=Vi + added.\n\nWhat happens empirically at Step0: V0=1\n\nS1: a1 =1 + number_of_faces(P0)*added_volume. Where number_of_faces(P0) =4, and added_volume is 1/8\n\nSo total added_bv1=4*1/8=1/2 =>V1=1+0.5=1.5\n\nNow the polyhedronP1 has number_of_faces S'1=24\n\nSo, moving to V2, adds number_of_faces(P1)*added_volume_p2. But added_volume_p2 is?\n\nHowever, each face of P1 is smaller? Each face of Pi+1 have edge lengths?\n\nWait, but in Pi, the added tetrahedrons at each step may varies sizes.\n\nFor example, in P0, edge length L. The added tetrahedron's edge length is L/2. When you then move to step1, in P1, faces are (for original parts) Those remaining on replaced faces, or from the added tetrahedrons.\n\nEach new face added in step1 is the three fresh face's of the tetrahe'drons. These three new faces are part of added tetraherons with edge length L/2.\n\nAt S1, the polyhedron P1 has:\n\nOriginal four tetrahedron's faces but each replaced into three subfaces. Each subface has edge length L/2 (since midpoints splits edges into halves). Because original edges of P0 was L, so after splitting into subfaces (the non-replaced outer triangles) each edge is (along original edges)→split between edges, which were at L, but the length between the midpoints would be L/2.\n\n Therefore, the original (remaining) subfaces after replacement in P0→P1 are triangles with edge length L/2.\n\nSo for S1’s faces: the original split faces and the new faces from the added tetrahedrons:\n\nP1's faces are two types:\n\n1. Residual subdivided faces from P0, which are triangles with edge length L/2, and;\n\n2. The three new faces from each added tetrahedron in P0→P1, whose edge length are also half (L/2).\n\nTherefore, all faces of S1 have edge length L/2. So, in proceeding Step2, Vi+1= Vi +Faces(P_i)*V_added.\n\nIn steps:\n\nStep0: V =1, Faces=4.\n\nStep1: V =1 +4*(1/8) =1 +0.5=1.5. Faces=4* (if Q increases to twofold), but actually according to previous, Faces=S1=24?\n\nWait, hold a horse! P1's Faces:\n\nFor original 4 faces in P0: Each face initially comprises retaining three residual subfaces (each edge length L/2) and three new faces from the added tetra. Each of these new tetra's non-base faces are also of edge length L/2, since the added tetra is edge length L/2.\n\nHence, each replaced face in P0 spawned 3 residual subfaces and 3 new faces. Therefore, total per original face:6 new faces.\n\nBut axially, So Faces of P1:4 original faces *6 =24。\n\nThus S1 has 24 faces, each edge length L/2. Similarly, in moving to S2, each face @ L/2 will have their midpoint triangle replaced by a tetrahedron with edge length (L/2)/2=L/4, each i volume will be= [ (L/4)^3*sqrt(2)/12] = [L^3*sqrt(2)/12 ]*(1/64 )= V0/64, since L^3*sqrt(2)/12=1.\n\nHence, each added tetrahedroni volume on stepier Step2 is 1/64.\n\nThen total added �Volume in step2 is faces(P1)*added_volume=24* (1/64)=24/64=3/8. Hence V2= V1 +3/8=1.5 +0.375=1.875=15/8.\n\nProceeding to Step3:\n\nIn step2, P2 has Faces=Q2= Faces(P1)*6=24*6=144, each with edge length L/4. The added tetrahedron volume each would be(1/8)^3 iteration-wise. Wait explicitty.\n\nBut after two reproductions: each added tetra in step 2 has edge length L/4, therefore Vol=1/64=1/(8^2), since initial L, step1 L/2 step2 L/4 etc. So volumetric scaling by 1/8 here each time.\n\nBut for step3: added volume(Faces(P2))*(1/(8^3)).\n\nWait. Previously:\n\nStep0: added_tetra=1/2 (4*(1/8))\n\nStep1: added=3/8 (24*(1/64)).Wait 1/8 was step1 Sized added?\n\nOr recognition that te Steps n added volumeS(faces(Number) * V(added each). at each step the faces multiply by 6, and the volume added per being (1/8)* (1/8)} of the previous added's volume.\n\nWait contrariwise, the faces multiply by 6, but the added virtues each Tagg'sigo te multiplier of 1/8 the prior volume.\n\nWait perhaps volume added_i= (prev Faces) *vol add'sii.\n\n volume add at step K: F_{k-1} * (1/8)^{k}\n\nWait moreprecisely, at each step k:\n\n volume_added_k= F_{k-1} * ( (1/2)^3 ), as the edge length scaling with 1/2 each time, per iteration.\n\nBut (1/2)^3=1/8, and weighted by F_{k-1}.\n\nButhow k’}— F_{0}=4,\n\n volume_added_1: 4*(1/8)=0.5,\n\n F_{1}=24,\n\n Volume_added_2:24/(8=24*(1/8)=3,\n\n But if at step2,_F1 that Faces are original of edge_length L/2, per tetra result in added tetrahedrons with their volumen (Lface edge /2)^3 indexes.\n\n Alternatively:\n\n conclusively, each additional tetra at stepk indexWith their edge_length equal to half the current'attuale step edge length. And Vol is, sinceovariano edge-length cubed: at stepk, edge_length= L/(2^k) and ergo the tetraVol av i wasV0/(8^k). Since V0=1, Vol_add por added tetra=1/(8^k).\n\n Thence, the number of TAg. etáleur_o stepék=F_{k-1}\n\n Thus volume_added due to pi o------------ to:\n\n V_total= V0 + Σ_{k=1}^inftyF_{k-1} * 1/(8^k) |\n\nBut since aim's os Vol to find V_due Till P3: thus oh for steps'reldom up to 3,\n\n V3= V0 + added_1Σ, added_2, added_3.\n\n F_{0}=4\n\n added_1=4*(1/8)=0.5\n\n F_{1}=4*6=24\n\n added_2 =24*(1/8^2)=24/64=0.375=3/8.\n\n F2=24*6=144.\n\n added_3=144*(1/8^3)=144/(512)= 0.28125=9/32.\n\n Consequently, V3=1 + 0.5 +0.375 +0.28125=1 + 0.5 i =1.5 +0.375=1.875 +0.28125=2.15625\n\n.\n\n2.15625 can be t+ turns to fraction.\n\nSince *t is equal to 9/32; let me repress this:\n\nV3=1 (step0) +4*(1/8) =1 +1/2=3/2 (step1) ? V1 = 3/2\n\nV2=3/2 + 24*(1/(8^2))=3/2 +24/64=3/2 +3/8= (12/8 +3/8)=15/8\n\nV3=15/8 +144/512. One thousand144/512=144 divided512 simplifies 144 /512=9/32 ?\n\nYes, 144/512 = (144 ÷16)=9, 512 ÷16=32, so 9/32.\n\nHence, V3=15/8 +9/32.\n\nConvert to common denominator:\n\n15/8=60/32.\n\n60/32 +9/32=69/32.\n\nTherefore, V3=69/32. But 69 and 32. Are they coprime? Explain si32'eese?\n\n69 factors:3×23. 32=2⁵\n\n They share no common factors, yes.\n\nSo m/n=69/32. n + m=69+32=101.\n\nBut why?\n\nWait but previous calculation.\n\n each added step:\n\nStep_k:\n\nAdded volumen = number of Faces in Pi_{k-1} * (1/8)^ ?\n\nWait Vi=1, then V1=1 +4*(1/8)=1 +0.5=1.5.\n\nQ1_faces=6*4=24.\n\nV2=1.5 +24*(1/8)^2=24*(1/64)=0.375=1.5+0.375=1.875=15/8。\n\nFaces_Q2= 24*6=144。\n\nV3=15/8 +144*(1/8)^3=144*(1/512 )=(144/512)=3*(48)/s→144 divided by 512:\n\n144 ÷16=9,512 ÷=32。144=9*16 ; 512=32*16. So gcd=16; simplify to9/32.\n\nTherefore V3=15/8 +9/32=60/32 +9/32=69/32.\n\nAnd69 and32，primeitatively, they have no common factors other than?\n\n32 is 2^5，69= 3*23，wellnone factors. so YES, coprime.\n\n thus m +n=69+32=101.\n\n This is the correct answer, I might be summarized tidily. Therefore,101。\n\n**Final Answer**\n\\boxed{101}"}}},{"rowIdx":3,"cells":{"id":{"kind":"number","value":3,"string":"3"},"source":{"kind":"string","value":"LIMO"},"instruction":{"kind":"string","value":"Set $A$ consists of $m$ consecutive integers whose sum is $2m,$ and set $B$ consists of $2m$ consecutive integers whose sum is $m.$ The absolute value of the difference between the greatest element of $A$ and the greatest element of $B$ is 99. Find $m.$"},"response":{"kind":"string","value":"Okay, so I need to solve this problem where there are two sets, A and B. Set A has m consecutive integers, and their sum is 2m. Set B has 2m consecutive integers, and their sum is m. The absolute difference between the greatest elements of A and B is 99. I have to find m. Hmm, let's break this down step by step.\n\nFirst, let me recall that the sum of consecutive integers can be found using the formula for an arithmetic series. The sum of n consecutive integers starting from a is given by n/2 * [2a + (n - 1)d], where d is the common difference. But since they are consecutive integers, d = 1. So the formula simplifies to n/2 * [2a + (n - 1)]. \n\nAlternatively, since the numbers are consecutive, the average of the series is the middle term, which is also the average of the first and last term. So the sum can be thought of as the average multiplied by the number of terms. That might be an easier way to approach it.\n\nLet me start with set A. It has m consecutive integers, and the sum is 2m. Let's denote the first term of set A as a. Then the terms are a, a+1, a+2, ..., a + (m - 1). The sum of these terms is the number of terms times the average of the first and last term. So sum = m * [(a + (a + m - 1)) / 2] = m * (2a + m - 1)/2. According to the problem, this sum is 2m. So:\n\nm * (2a + m - 1)/2 = 2m\n\nLet me simplify this equation. Multiply both sides by 2:\n\nm * (2a + m - 1) = 4m\n\nDivide both sides by m (assuming m ≠ 0, which is reasonable since m is the number of terms in set A):\n\n2a + m - 1 = 4\n\nNow solve for a:\n\n2a = 4 - m + 1\n2a = 5 - m\na = (5 - m)/2\n\nSo the first term of set A is (5 - m)/2. Since the elements are integers, a must be an integer. Therefore, (5 - m) must be even, so 5 - m is even ⇒ m is odd. So m is an odd integer. That's useful information.\n\nNow, the greatest element of set A is a + m - 1. Plugging in a:\n\nGreatest element of A = (5 - m)/2 + m - 1 = (5 - m)/2 + (2m - 2)/2 = (5 - m + 2m - 2)/2 = (m + 3)/2\n\nSo the greatest element of A is (m + 3)/2. That simplifies things.\n\nNow moving on to set B. Set B has 2m consecutive integers with a sum of m. Let's denote the first term of set B as b. Then the terms are b, b+1, ..., b + (2m - 1). The sum of these terms is 2m * [(b + (b + 2m - 1))/2] = 2m * (2b + 2m - 1)/2 = m * (2b + 2m - 1). The problem states that this sum is m. So:\n\nm * (2b + 2m - 1) = m\n\nAgain, assuming m ≠ 0, divide both sides by m:\n\n2b + 2m - 1 = 1\n\nSolve for b:\n\n2b = 1 - 2m + 1\n2b = 2 - 2m\nb = (2 - 2m)/2 = 1 - m\n\nSo the first term of set B is 1 - m. Therefore, the greatest element of set B is b + 2m - 1 = (1 - m) + 2m - 1 = (1 - 1) + (2m - m) = m. So the greatest element of B is m.\n\nNow, according to the problem, the absolute difference between the greatest elements of A and B is 99. So:\n\n| (m + 3)/2 - m | = 99\n\nLet me compute this expression inside the absolute value:\n\n(m + 3)/2 - m = (m + 3 - 2m)/2 = (-m + 3)/2\n\nSo | (-m + 3)/2 | = 99\n\nMultiply both sides by 2:\n\n| -m + 3 | = 198\n\nWhich is equivalent to:\n\n| 3 - m | = 198\n\nSo, 3 - m = 198 or 3 - m = -198\n\nSolving for m:\n\nCase 1: 3 - m = 198 ⇒ -m = 195 ⇒ m = -195\n\nBut m is the number of terms in set A, which must be a positive integer. So discard this solution.\n\nCase 2: 3 - m = -198 ⇒ -m = -201 ⇒ m = 201\n\nSo m = 201. Let me verify if this is valid.\n\nFirst, check the first term of set A: a = (5 - m)/2 = (5 - 201)/2 = (-196)/2 = -98\n\nSo set A starts at -98 and has 201 consecutive integers. The greatest element of A is (m + 3)/2 = (201 + 3)/2 = 204/2 = 102. Wait, but if the first term is -98 and there are 201 terms, the last term is -98 + 200 = 102. That matches.\n\nSum of set A: The average is ( -98 + 102 ) / 2 = 4/2 = 2. Number of terms is 201. So sum is 2*201 = 402. Which should be equal to 2m = 2*201 = 402. Correct.\n\nNow set B: first term is 1 - m = 1 - 201 = -200. Number of terms is 2m = 402. The last term is -200 + 401 = 201. So the greatest element of B is 201. The absolute difference between 102 and 201 is |102 - 201| = 99. Which is as per the problem. So this checks out.\n\nBut wait, the problem says the absolute difference between the greatest elements of A and B is 99. The greatest element of A is 102, of B is 201. 201 - 102 = 99. So that's correct.\n\nTherefore, m = 201. So the answer is 201. Hmm, but let me check if I did everything correctly.\n\nWait, let me re-examine the steps. For set A, the greatest element was calculated as (m + 3)/2, which for m=201 gives (201 + 3)/2 = 204/2 = 102. Then set B's greatest element is m=201, which is 201. The difference is 201 - 102 = 99. So absolute value is 99. Correct.\n\nBut wait, in the problem statement, set B has 2m consecutive integers. When m=201, set B has 402 terms. Starting at 1 - 201 = -200, so terms from -200 to 201 inclusive. Let's check the sum. The sum of numbers from -200 to 201. Wait, how many terms are there? From -200 to 201 inclusive, that's 201 - (-200) + 1 = 201 + 200 +1 = 402 terms. Correct. The sum can be calculated as (number of terms)/2 * (first term + last term) = 402/2 * (-200 + 201) = 201 * 1 = 201. But the sum is supposed to be m, which is 201. So that's correct.\n\nTherefore, all conditions are satisfied. So m=201 is indeed the correct answer.\n\nBut let me just check if there are any other possible solutions. The absolute value equation |3 - m| = 198 gave us m=201 and m=-195, but m must be positive. So only m=201. So that's unique.\n\nTherefore, the answer is 201.\n\n**Final Answer**\n\\boxed{201}"}}},{"rowIdx":4,"cells":{"id":{"kind":"number","value":4,"string":"4"},"source":{"kind":"string","value":"LIMO"},"instruction":{"kind":"string","value":"Let $S$ be the set of all positive rational numbers $r$ such that when the two numbers $r$ and $55r$ are written as fractions in lowest terms, the sum of the numerator and denominator of one fraction is the same as the sum of the numerator and denominator of the other fraction. The sum of all the elements of $S$ can be expressed in the form $\\frac{p}{q},$ where $p$ and $q$ are relatively prime positive integers. Find $p+q.$"},"response":{"kind":"string","value":"Okay, so the problem is about finding all positive rational numbers r such that when you write r and 55r as fractions in their lowest terms, the sum of the numerator and denominator of one is equal to the sum of the numerator and denominator of the other. Then we need to find the sum of all these r and express it as p/q with p and q coprime, then give p+q.\n\nHmm. So, first, let me understand what this means. Let's take a rational number r, which can be written as a/b in lowest terms, meaning that a and b are coprime positive integers. Similarly, 55r would be written as (55a)/b, but since it's in lowest terms, we need to divide 55a and b by their greatest common divisor. So, 55r would be (55a/gcd(55a, b)) / (b/gcd(55a, b)).\n\nThe problem states that the sum of the numerator and denominator of one of these fractions equals the sum for the other. So, either a + b equals the numerator of 55r plus its denominator, or vice versa. That is, either:\n\na + b = (55a/gcd(55a, b)) + (b/gcd(55a, b))\n\nor\n\n(55a/gcd(55a, b)) + (b/gcd(55a, b)) = a + b\n\nSo, that's equivalent to saying:\n\nEither the sum for r is equal to the sum for 55r, or their sums are equal. But since equality is symmetric, it's just one condition: the two sums must be equal. So, the idea is that when simplifying both r and 55r, the sum of numerator and denominator for each, in their reduced forms, must be the same.\n\nSo, how can we approach this? Let's denote r as a/b in lowest terms. So, a and b are coprime. Then, 55r is 55a/b. Let's call the reduced form of 55a/b as c/d, where c and d are coprime. Then, we must have that a + b = c + d. Or c + d = a + b. But since they are sums, it's the same. So, we can say that the sum a + b must equal the sum c + d.\n\nSo, perhaps, need to set up equations for this. Let me think.\n\nSince c/d is the reduced form of 55a/b, gcd(55a, b) must divide both 55a and b. Therefore, gcd(55a, b) is gcd(55, b) since a and b are coprime.\n\nWait, let me check that. Since a and b are coprime, then gcd(55a, b) = gcd(55, b) because any common divisor of 55a and b must divide both 55a and b, but since a and b are coprime, the divisor must divide 55 and b.\n\nYes, that's correct. So that gcd(55a, b) = gcd(55, b). Therefore, the numerator and denominator of 55r are 55a divided by gcd(55, b) and b divided by gcd(55, b). Hence:\n\nNumerator: 55a / gcd(55, b)\nDenominator: b / gcd(55, b)\nSo, c = 55a / g, d = b / g, where g = gcd(55, b)\n\nTherefore, c + d = (55a + b) / g\n\nTherefore, the condition is that a + b = (55a + b) / g, where g = gcd(55, b)\n\nSo, let’s write down the equation:\n\na + b = (55a + b)/g\n\nMultiply both sides by g:\n\ng(a + b) = 55a + b\n\nWhich is:\n\nga + gb = 55a + b\n\nRearranged:\n\n(ga - 55a) + (gb - b) = 0\n\na(g - 55) + b(g - 1) = 0\n\nSo,\n\na(55 - g) = b(g - 1)\n\nWait: When moved the terms:\n\na(g - 55) + b(g - 1) = 0 → a(55 - g) + b(1 - g) = 0 ?\n\nHmm, maybe better to rederive the equation.\n\nStarting from:\n\ng(a + b) = 55a + b\n\nSo,\n\ng a + g b = 55a + b\n\nThen grouping terms:\n\ng a -55a = b - g b\n\nWhich is:\n\na(g - 55) = b(1 - g)\n\nMultiply both sides by -1:\n\na(55 - g) = b(g - 1)\n\nSo,\n\na(55 - g) = b(g - 1)\n\nSo, let's note that here, g is the gcd(55, b), which divides 55. So g is a divisor of 55, which can be 1, 5, 11, or 55.\n\nTherefore, possible values of g: 1,5,11,55. So, we can consider each value of g, then obtain equations relating a and b, given that a/b is in lowest terms (so a and b are coprime).\n\nOur main equation is a(55 - g) = b(g - 1)\n\nLet’s consider each possible g.\n\nCase 1: g = 1 (gcd(55, b) =1)\n\nThen,\n\na(55 -1)= b(1 -1) → a(54)=b(0) → 54a=0. But a is positive integer, so this is impossible. Therefore, there's no solution when g =1.\n\nCase 2: g =5 (gcd(55, b)=5)\n\nThen,\n\na(55 -5)=b(5 -1) → a*50=b*4 → 50a=4b → 25a=2b\n\nSo, 25a=2b ⇒ b = (25a)/2. Since b must be integer, so a must be even. Let a=2k, then b=(25*2k)/2=25k.\n\nBut since a and b must be coprime. Let a =2k and b=25k. Then gcd(2k,25k)=gcd(2,25)*k=1*k, but k must divide both 2k and 25k. So, to ensure that gcd(a, b)=1, we need k=1. Because if k >1, then gcd(2k,25k)=k, which must be 1. Therefore k=1.\n\nThus, the only possible a and b in this case are a=2*1=2, b=25*1=25.\n\nSo, checked gcd(2,25)=1, correct.\n\nThus, when g=5, the fraction r is a/b=2/25.\n\nNow let's verify:\n\nOriginal r=2/25, which is in lowest terms. 55r=55*(2)/25=110/25=22/5 in reduced terms. Wait, 110/25 simplifies to 22/5, correct. The sum of numerator and denominator for r is 2+25=27; sum for 55r is 22+5=27. So, yes, both sums are equal. So this is a valid solution.\n\nCase 3: g=11. Then, equation becomes:\n\na(55 -11)=b(11 -1) → a*44=b*10 → 44a=10b → 22a=5b.\n\nThus, 22a=5b. Then, since a and b must be coprime here (for r=a/b to be in lowest terms), we have:\n\n22a=5b -> b=(22/5)a. But a and b are integers, so a must be divisible by 5. Let a=5k, then b=(22/5)*5k=22k.\n\nThus, a=5k, b=22k. Then, gcd(a, b)=gcd(5k,22k)=gcd(5,22)*k=1*k=k. So, for a/b to be reduced, we need k=1, so that gcd(5k,22k)=k=1. Hence, the only solution here is a=5, b=22.\n\nCheck gcd(5 and 22)=1, yes. Compute r=5/22. Now, 55r=55*(5)/22=275/22 reduces to 25/2 (275 divided by 22: divide both by gcd(275,22). gcd(275,22). Let me compute: 275 is divisible by 5? 275=5×55, 22 is 2×11. GCD(5×55,2×11). The common divisors? 55 and 22 have gcd 11. Wait, 275=5*55=5*5*11, 22=2*11. So gcd is 11. Thus 275/22 reduces to (275/11)/(22/11)=25/2. Sum numerator and denominator for 5/22 is 5+22=27. For 25/2 it's 25+2=27. Correct. So indeed, another solution.\n\nCase 4: g=55 (gcd(55, b)=55). Then,\n\nequation:\n\na(55-55)=b(55-1) → a*0= b*54 → 0=54b. Since b is positive integer, no solution. So, no case here.\n\nSo, possible solutions only occur when g=5 and g=11, each giving one rational number: r=2/25 and r=5/22. So, the set S has elements 2/25 and 5/22. So, sum of all elements would be 2/25 +5/22.\n\nTo compute this, let's get denominator LCM of 25 and 22. 25 is 5², 22 is 2×11. So LCM is 2×5²×11=550. So 2/25 = 44/550 and 5/22=125/550. Adding them gives 44+125=169. Then, 169/550. Then and check how's 169 and 550 related.\n\nGCD of 169 and 550. 169 is 13², 550 is 2×5²×11. They share no common prime factors. So yes, 169/550 is the reduced form. So p=169, q=550, therefore p+q=169+550=719.\n\nWait, but hold on. Let me cross check all steps.\n\nSolution when g=5: a=2, b=25? Sum 2+25=27. 55r=110/25 reduce to 22/5, sum 22+5=27. Good.\n\nSimilarly, case g=11: a=5, b=22. Sum same too. So both fractions 2/25 and 5/22 are in S. Are there other fractions?\n\nWait, I only found two elements in S. Is that all?\n\nBut let me think again. When we solved for each case (g=5 and 11), under the equation:\n\na(55 -g)=b(g -1).\n\nIn each case, we considered g=5 and derived a=2, b=25. For g=11, a=5, b=22.\n\nBut maybe there is an assumption here. Because In the equation, after setting 25a=2b when g=5, we see that since 25 and 2 are coprime, the minimal solution is a=2, b=25. Then equations: k.\n\nBut maybe are there other solutions where a and b are multiples by coprime.\n\nWait. Let me recheck for the case of g=5:\n\nWe had 25a=2b ⇒ 25a =2b ⇒ a=2k, b=25k. But since gcd(a,b)=1 implies gcd(2k,25k)=k. So for them to be coprime, k must be 1. So only possible solution is a=2, b=25.\n\nSame for case g=11:\n\n22a=5b ⇒ (gcd terms etc) a=5k, b=22k ⇒ gcd(a,b)=k. Need k=1, so a=5, b=22.\n\nTherefore, only two solutions. So sum is 2/25 +5/22.\n\nCompute that sum. Converting 2/25 into 44/550 (25×22=550), and 5/22 is 125 (5×25=125)/550? Wait, no. Wait, converting 2/25 to fractions with denominator 550 (LCD of 25 and 22):\n\n25=5², 22=2×11, LCM is 5²×2×11=550.\n\nSo 2/25 = (2×22)/(25×22)=44/550.\n\n5/22=(5×25)/(22×25)=125/550.\n\n44 +125=169. So total 169/550.\n\n169 and 550: reduced? GCD(169,550). Divisors of 169: 13². 550:55×10=5×11×2×5. So, no common factors. So yes, 169/550 reduced. So p=169, q=550, sum p+q=719.\n\nBut wait, the answer description says \"The sum of all the elements of S can be expressed in the form p/q, where p and q are relatively prime positive integers. Find p+q.\" So answer should be 719.\n\nBut hang on, but let's check again.\n\nIs S only the two elements 2/25 and 5/22? Let me make sure if we haven't missed possibilities.\n\nSuppose, perhaps, there could be more fractions, for example where or fractions where numerator and denominator have other divisors.\n\nBut given how we broke down the problem, since gcd(55, b) can only be 1,5,11, or 55, which are divisors of 55. For each possible gcd, we have:\n\nIf gcd=5, gives one solution,\n\ngcd=11 gives another,\n\nwith gcd=1 and 55 yielding no solutions.\n\nThus only two solutions.\n\nHence sum is 2/25 +5/22=169/550, p+q=719.\n\nSo unless there's another approach where more solutions exist.\n\nAlternatively, let me assume that maybe there's a fraction where r and 55r have same sum. So alternative approach:\n\nLet r=a/b, reduced. Then 55r =c/d, reduced. Then a + b = c + d.\n\nFrom 55r=c/d ==> 55 a/b = c/d. So 55a d = c b. Since c and d are coprime, because reduced fraction.\n\nBut r=a/b is also reduced. So possible relationships.\n\nHmm, but 55a/b = c/d, which implies that c/d=55a/b --> cross multiply: 55a d = c b\n\nBut c and d are coprime, therefore the divisors... Perhaps can model this equation? But since you cross multiply, it's 55a*d = c*b. Then whether can represent the mapping between a,b,c,d.\n\nBut maybe not too useful compared to prior approach.\n\nBut yes, problem seems to have that S consists of 2/25 and 5/22.\n\nBut just to check if there's another rational number. Let me consider some example. Take r=1/55. Then 55*1/55=1/1. The sum of numerator and denominator for r is 1+55=56. For 55r=1/1, sum is 1+1=2. So not equal.\n\nAnother example, r=1/5. These would translate to 55r=11/1, sum for r=1+5=6, sum for 55r=11+1=12. Not equal.\n\nTake 5/5, but that's not reduced. Disregard.\n\nTake r=3/7. Then, 55*3/7=165/7. That is already reduced (since gcd(165,7)=1?), 165 – yes, 7 divides 165? 165 divided by 7 is 23.57~=23. So 165=7×23 +4. So 165 and7 are coprime. Sum: 3+7=10 vs. 165+7=172. Not equal.\n\nWait. How about 2/25: already and 5/22. Any others?\n\nTake r=25/2, but that's not positive— but question says \"positive\", so fractions, same notation. Wait, but 25/2 is same as 2/25 but upside down. But positive, cases are same. Wait, fractions of in lowest terms as a/b where a and b are positive.\n\nBut we have r is positive, so all a and b are positive. So 25/2 is a different r, but would you have 55*25/2=. Wait, 55*25=1375/2.\n\nBut in reduced terms, whether sum equals? But no.\n\nBut, hang on, when I inverted the fractions, suppose 55*(25/2)=1375/2, reduced.\n\nSum for 25/2: 25+2=27. 1375 and 2: g= gcd(1375,2)=1. Then sum is 1375 +2=1377.\n\nNot equal. Hence no.\n\nSo, only the two as found. Hence sum is 169+550=719. So uhm, yeah.\n\n**Final Answer**\n\\boxed{719}"}}},{"rowIdx":5,"cells":{"id":{"kind":"number","value":5,"string":"5"},"source":{"kind":"string","value":"LIMO"},"instruction":{"kind":"string","value":"Let $n=2^{31}3^{19}.$ How many positive integer divisors of $n^2$ are less than $n_{}$ but do not divide $n_{}$ ?"},"response":{"kind":"string","value":"Okay, let's try to figure out this problem. The question is: Let \\( n = 2^{31} \\times 3^{19} \\). How many positive integer divisors of \\( n^2 \\) are less than \\( n \\) but do not divide \\( n \\)?\n\nFirst, I need to understand what's being asked here. We have to find divisors of \\( n^2 \\) that are less than \\( n \\) but aren't divisors of \\( n \\). So, essentially, these are numbers that divide \\( n^2 \\) but aren't factors of \\( n \\) itself and are smaller than \\( n \\).\n\nLet me recall some number theory concepts. If a number \\( n \\) has a prime factorization \\( n = p_1^{a_1} p_2^{a_2} \\dots p_k^{a_k} \\), then the number of divisors of \\( n \\) is \\( (a_1 + 1)(a_2 + 1) \\dots (a_k + 1) \\). Similarly, \\( n^2 \\) would have a prime factorization \\( n^2 = p_1^{2a_1} p_2^{2a_2} \\dots p_k^{2a_k} \\), so its number of divisors would be \\( (2a_1 + 1)(2a_2 + 1) \\dots (2a_k + 1) \\).\n\nGiven that \\( n = 2^{31} \\times 3^{19} \\), then \\( n^2 = 2^{62} \\times 3^{38} \\). So, the number of divisors of \\( n \\) is \\( (31 + 1)(19 + 1) = 32 \\times 20 = 640 \\). The number of divisors of \\( n^2 \\) would be \\( (62 + 1)(38 + 1) = 63 \\times 39 = 2457 \\).\n\nNow, we need to find the number of divisors of \\( n^2 \\) that are less than \\( n \\) but do not divide \\( n \\). Let me think about how to approach this.\n\nI remember that for any number \\( m \\), the divisors come in pairs that multiply to \\( m \\). For \\( n^2 \\), the divisors less than \\( n \\) would pair with divisors greater than \\( n \\) such that their product is \\( n^2 \\). So, the total number of divisors of \\( n^2 \\) less than \\( n \\) should be equal to the number of divisors greater than \\( n \\). Since \\( n^2 \\) is a perfect square, \\( n \\) itself is the square root, so the number of divisors less than \\( n \\) would be \\( \\frac{\\text{number of divisors of } n^2 - 1}{2} \\). Wait, because \\( n \\) is a divisor of \\( n^2 \\), so we subtract 1 (to exclude \\( n \\) itself) and divide by 2. So, that would be \\( \\frac{2457 - 1}{2} = 1228 \\).\n\nBut these 1228 divisors of \\( n^2 \\) that are less than \\( n \\) include divisors that also divide \\( n \\). So, we need to subtract the number of divisors of \\( n \\) that are less than \\( n \\) to get the ones that do not divide \\( n \\).\n\nWait, the number of divisors of \\( n \\) that are less than \\( n \\) is \\( 640 - 1 = 639 \\), since we exclude \\( n \\) itself. Therefore, the number of divisors of \\( n^2 \\) that are less than \\( n \\) but do not divide \\( n \\) would be \\( 1228 - 639 = 589 \\).\n\nBut let me verify this approach step by step to make sure I haven't made a mistake.\n\nFirst, confirm the number of divisors of \\( n \\): \\( (31 + 1)(19 + 1) = 32 \\times 20 = 640 \\). Correct.\n\nNumber of divisors of \\( n^2 \\): \\( (62 + 1)(38 + 1) = 63 \\times 39 = 2457 \\). Correct.\n\nDivisors of \\( n^2 \\) come in pairs multiplying to \\( n^2 \\). So, divisors less than \\( n \\) pair with divisors greater than \\( n \\). Since \\( n^2 \\) is a square, \\( n \\) is the square root, so exactly one divisor is equal to \\( n \\). Therefore, the total number of divisors less than \\( n \\) is equal to the number of divisors greater than \\( n \\), which is \\( (2457 - 1)/2 = 1228 \\). That seems right.\n\nNow, the divisors of \\( n^2 \\) less than \\( n \\) include all the divisors of \\( n \\) (except \\( n \\) itself) and some more divisors that don't divide \\( n \\). So, to find the number of divisors of \\( n^2 \\) less than \\( n \\) but not dividing \\( n \\), subtract the number of divisors of \\( n \\) (excluding \\( n \\)) from the total number of divisors of \\( n^2 \\) less than \\( n \\).\n\nNumber of divisors of \\( n \\) less than \\( n \\): 640 - 1 = 639. So, 1228 - 639 = 589. So, the answer should be 589. Hmm.\n\nBut let me think again. Is every divisor of \\( n \\) a divisor of \\( n^2 \\)? Yes, because if d divides n, then n = d * k, so n^2 = d * k * n, so d divides n^2. So, all divisors of n are indeed divisors of n^2.\n\nTherefore, the logic is: total divisors of n^2 less than n are 1228. Subtract the number of divisors of n that are less than n (which is 639), giving 589 divisors of n^2 less than n that do not divide n.\n\nWait, but let me check with an example to ensure this method works.\n\nTake a smaller number, say n = 2^1 * 3^1 = 6.\n\nThen n^2 = 36 = 2^2 * 3^2. Divisors of n: 1, 2, 3, 6. Number of divisors: 4.\n\nDivisors of n^2: 1, 2, 3, 4, 6, 9, 12, 18, 36. Number of divisors: 9.\n\nDivisors of n^2 less than n=6: 1, 2, 3, 4. So, 4 divisors.\n\nBut divisors of n less than n: 1, 2, 3. So, 3 divisors.\n\nTherefore, the answer should be 4 - 3 = 1. Checking which one: the divisors of 36 less than 6 but not dividing 6 are 4. So, correct.\n\nTherefore, the method works here. So, applying the same reasoning to the original problem should be valid.\n\nTherefore, the answer is 1228 - 639 = 589. So, 589. But wait, let me check the arithmetic again.\n\n2457 - 1 = 2456. 2456 / 2 = 1228. Correct.\n\n640 - 1 = 639. Correct.\n\n1228 - 639: 1228 - 600 = 628; 628 - 39 = 589. Correct.\n\nHence, the answer should be 589. Hmm.\n\nWait, but just to be thorough, let me consider another example.\n\nTake n = 2^2 * 3^1 = 12.\n\nn^2 = 144 = 2^4 * 3^2.\n\nDivisors of n: 1, 2, 3, 4, 6, 12. Number of divisors: 6.\n\nDivisors of n^2: 1, 2, 3, 4, 6, 8, 9, 12, 16, 18, 24, 36, 48, 72, 144. Number of divisors: 15.\n\nNumber of divisors of n^2 less than 12: 1, 2, 3, 4, 6, 8, 9. That's 7 divisors.\n\nNumber of divisors of n less than 12: 5.\n\nTherefore, the answer should be 7 - 5 = 2. Checking which ones: 8 and 9. These are divisors of 144 less than 12 that do not divide 12. Correct.\n\nSo, the formula works here as well: total divisors of n^2 less than n: (15 -1)/2 = 7. Divisors of n less than n: 5. Answer: 7 -5 =2. Correct.\n\nTherefore, the method seems valid.\n\nTherefore, returning to the original problem, the answer should be 589. But let me just cross-verify once more with the exponents.\n\nGiven n = 2^{31} * 3^{19}.\n\nNumber of divisors of n: (31 +1)(19 +1)=32*20=640. Correct.\n\nNumber of divisors of n^2: (62 +1)(38 +1)=63*39=2457. Correct.\n\nDivisors of n^2 less than n: (2457 -1)/2=2456/2=1228. Correct.\n\nDivisors of n less than n: 640 -1=639. Correct.\n\nTherefore, the answer is 1228 - 639=589. So, 589.\n\nBut wait, let me think if there's another way to compute this. Maybe using exponents.\n\nA divisor of n^2 can be written as 2^a * 3^b where 0 31 or b >19. So, the divisors of n^2 that do not divide n are exactly those where a >31 or b >19.\n\nBut we need to count those divisors which are also less than n.\n\nSo, perhaps another approach is to compute the number of divisors of n^2 that are less than n and have either a >31 or b >19.\n\nSo, total divisors of n^2 less than n: 1228.\n\nNumber of these that divide n: 639.\n\nTherefore, 1228 -639=589, which is the same as before.\n\nAlternatively, using inclusion-exclusion: the number of divisors of n^2 less than n with a >31 plus the number with b >19 minus the number with both a>31 and b>19.\n\nBut maybe this approach is more complicated, but let's try.\n\nFirst, compute the number of divisors of n^2 with a >31 and 2^a *3^b 31, so a ranges from 32 to 62. But we also need 2^a *3^b 2^{a -31} *3^{b -19} 31, let me set x = a -31 >=1, and y = b -19. But since 2^{x} *3^{y} =1, y can be negative or non-positive.\n\nWait, perhaps it's better to rewrite the inequality as 2^{a}/2^{31} *3^{b}/3^{19} 31, x =a -31 >=1, and 3^{b -19} =2^x.\n\nBut since 3^{19 -b} must be an integer, and 2^x is also an integer, so we need 3^{19 -b} >=2^x where x >=1 and b =2^x, and then b = log_3(2^x) => 19 -b >=x * log_3(2). Therefore, b 3^{b -19} =32, 31 -a 3^{19 -b} >=2.\n\nWhich implies that 19 -b >=1 (since 3^1=3 >=2). So, 19 -b >=1 =>b =32, the maximum b is 18. Wait, but this seems confusing.\n\nWait, let's take an example. Let a=32. Then, 31 -a= -1. So, 2^{31 -a}=1/2. Therefore, 3^{b -19} =2. So, 19 -b >=1 => b =4. Since 3^1=3 =4. So, 19 -b >=2 =>b 2^{-3}=1/8. So, 3^{19 -b} >=8. 3^1=3 =8. So, 19 -b >=2 =>b =8. 3^2=9 >=8, 3^1=3 =2 =>b =8 requires 19 -b >=2, which is b =16. 3^2=9 =16. So, 19 -b >=3 =>b =32. 3^3=27 =32. So, 19 -b >=4 =>b 31 is equal to the number of divisors of n^2 where a ranges from32 to62 and b ranges from0 to such that 2^a *3^b 31, b 2^{a -31} 31 and a a -31 a d=n. But d=n is a divisor of n, so it is excluded. Therefore, all other divisors should pair up. Therefore, the number of non-divisors of n in n^2 should be even. But 1817 is odd. Contradiction. Therefore, my initial assumption must be wrong. Where is the mistake?\n\nWait, maybe the count of divisors of n is wrong? Wait, no. n=2^{31}3^{19}, so the number of divisors is (31+1)(19+1)=32*20=640. Correct.\n\nn^2=2^{62}3^{38}, number of divisors is(62+1)(38+1)=63*39=2457. Correct.\n\nTherefore, 2457 -640=1817, which is odd. Therefore, there is a contradiction. Therefore, my reasoning must be flawed. Maybe I need to re-examine the pairing argument.\n\nWait, if d is a divisor of n^2 not dividing n, then n^2/d is also a divisor of n^2 not dividing n. So, (d, n^2/d) form pairs. Therefore, the total number of such divisors should be even. Therefore, 1817 must be even. But 1817 divided by2 is908.5, which is not an integer. Hence, contradiction. Therefore, my calculation is wrong.\n\nWait, but 2457 is odd, 640 is even, so2457 -640=1817 is odd. But this contradicts the pairing. Therefore, where is the error?\n\nWait, maybe the problem is that some of the divisors d of n^2 not dividing n satisfy d =n^2/d, but that would imply d =n, which divides n. Therefore, there are no such divisors. Therefore, all divisors must come in pairs, so the total number should be even. Therefore, the calculation must be wrong.\n\nBut 2457 -640=1817, which is odd. Therefore, this suggests that the original problem is wrong? That can't be. Wait, no. Wait, maybe I miscalculated the number of divisors of n^2.\n\nWait, n=2^{31}3^{19}. So, n^2=2^{62}3^{38}. Then number of divisors is(62+1)(38+1)=63*39=2457. 63*39: 60*39=2340, 3*39=117, 2340+117=2457. Correct.\n\nNumber of divisors of n: (31+1)(19+1)=32*20=640. Correct.\n\n640 is even. 2457 is odd. 2457-640=1817 is odd. So, contradiction.\n\nWait, so perhaps my mistake is in assuming that all divisors of n^2 that don't divide n come in pairs. But in reality, if d is a divisor of n^2 not dividing n, then n^2/d is also a divisor of n^2 not dividing n. Therefore, if d ≠n^2/d, they form a pair. If d =n^2/d, then d =n, but d =n divides n, so it's excluded. Therefore, the number of such divisors must be even. Therefore, 1817 must be even. Hence, the result 1817 is impossible. Therefore, there must be a miscalculation.\n\nWait, but 2457-640=1817 is definitely correct. Therefore, the contradiction suggests an error in the problem statement or my understanding.\n\nWait, hold on. Wait, divisors of n^2 include all the divisors of n, right? Because if d divides n, then d divides n^2. Yes. Therefore, the number of divisors of n^2 that are not divisors of n is2457 -640=1817. But since n^2 is a square, the number of divisors less than n is equal to the number of divisors greater than n. Which is(2457 -1)/2=1228. Therefore, the number of divisors less than n is1228, which includes divisors of n (which are639) and others. Therefore, the number of divisors of n^2 less than n that do not divide n is1228 -639=589. And the number of divisors of n^2 greater than n that do not divide n is also589. Then, total divisors of n^2 not dividing n would be589 +589=1178. But 1178 ≠1817. Therefore, discrepancy.\n\nWait, so where is the problem?\n\nWait, total divisors of n^2 not dividing n:1817.\n\nDivisors of n^2 not dividing n and less than n:589.\n\nDivisors of n^2 not dividing n and greater than n:589.\n\nDivisors of n^2 equal to n:1 (but n divides n, so it's excluded).\n\nBut 589 +589=1178≠1817. Therefore, my previous reasoning is flawed.\n\nWait, so the discrepancy is1817 -1178=639. Which is exactly the number of divisors of n (excluding n itself). Wait, no. Wait, 1817 =1178 + 639? 1178 +639=1817. Yes. Therefore, this suggests that there are 639 divisors of n^2 not dividing n that are equal to... what? But n^2 divisors not dividing n can't be equal to divisors of n. Wait, this is confusing.\n\nWait, perhaps my original approach is wrong. Let me clarify.\n\nTotal divisors of n^2:2457.\n\nDivisors of n:640. All of these are also divisors of n^2.\n\nTherefore, the remaining divisors of n^2 are2457 -640=1817, which do not divide n.\n\nThese 1817 divisors come in pairs (d, n^2/d) where d n, or vice versa.\n\nBut the number of such pairs should be equal to the number of divisors less than n which do not divide n, multiplied by2. But since n^2 is a perfect square, only n is the square root, so all other divisors pair up.\n\nBut according to earlier count, divisors of n^2 less than n:1228. This includes divisors of n (639) and those that don't divide n (589). Similarly, divisors greater than n:1228, which includes 639 divisors of n (since each divisor of n greater than1 has a complement divisor less than n) and 589 that don't divide n.\n\nWait, no. Wait, divisors of n greater than n would only be n itself, but n is not greater than n. Wait, divisors of n are from1 to n. So, divisors of n are all less than or equal to n. Therefore, divisors of n^2 greater than n are all the ones not dividing n, except for those that are multiples.\n\nWait, this is getting too confusing. Maybe we need to visualize.\n\nImagine the set of divisors of n^2. They can be partitioned into three categories:\n\n1. Divisors that are also divisors of n and less than n:639.\n\n2. The divisor n itself:1.\n\n3. Divisors that do not divide n:1817.\n\nNow, the divisors that do not divide n can be split into those less than n and those greater than n. Let x be the number of divisors of n^2 that do not divide n and are less than n. Then, since each such divisor pairs with one greater than n, the number of divisors greater than n is also x. Additionally, the divisor n itself is in the middle.\n\nBut the total number of divisors of n^2 is2457=639 +1 +x +x.\n\nTherefore, 2457=640 +2x =>2x=2457 -640=1817 =>x=1817/2=908.5. But x must be an integer. Contradiction.\n\nTherefore, this suggests that there's an error in our assumption that every divisor of n^2 not dividing n pairs with another such divisor. However, since 1817 is odd, this is impossible. Therefore, the mistake must be in the problem statement or my calculations.\n\nWait, but the problem statement is given, so likely my mistake is in the calculations.\n\nWait, let's double-check the number of divisors.\n\nGiven n=2^{31}3^{19}, so n^2=2^{62}3^{38}.\n\nNumber of divisors of n^2: (62 +1)(38 +1)=63*39=2457. Correct.\n\nNumber of divisors of n: (31 +1)(19 +1)=32*20=640. Correct.\n\nSo, 2457 -640=1817. Correct.\n\nThe contradiction arises because 1817 is odd, but according to pairing, it should be even. Therefore, there must be a divisor d of n^2 not dividing n such that d =n^2/d. But d=n^2/d imp | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/esko-automation-engine/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click | Automation Engine | LinkedIn Skip to main content LinkedIn Esko in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Automation Engine Workflow Management Software by Esko See who's skilled in this Add as skill Learn more Report this product About Automation Engine is designed to maximize automation within your prepress department and beyond – supplying right first time proofs to your customers and high-quality print-ready files for your digital, flexo, offset, and gravure presses. Automation Engine enables you to standardize your processes, remove time wasted activities from your prepress, and minimize pre-production errors. Media Products media viewer No more previous content Automation Engine Achieving more with Automation Engine SaaS Take a look at how our new Automation Engine SaaS helps take your prepress to a whole new level. No more next content Similar products n8n n8n Workflow Management Software Pipefy Pipefy Workflow Management Software Jotform Workflows Jotform Workflows Workflow Management Software TeamViewer Frontline TeamViewer Frontline Workflow Management Software Value Stream Management Value Stream Management Workflow Management Software ApprovalMax ApprovalMax Workflow Management Software Sign in to see more Show more Show less Esko products WebCenter WebCenter Product Lifecycle Management (PLM) Software LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/categories/web-application-firewalls?trk=products_details_guest_other_products_by_org_section_product_link_result-card_subtitle-click#main-content | Best Web Application Firewalls (WAF) | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Chief Information Security Officer (13) Chief Information Officer (7) Security Professional (6) Information Technology Specialist (6) Chief Technology Officer (5) See all products Find top products in Web Application Firewalls (WAF) category Software used to protect web-based applications and application programming interfaces from threats. - Monitor and filter traffic to and from web applications - Automatically block malicious or anomalous application access and activity 79 results Cloudflare WAF Web Application Firewalls (WAF) by Cloudflare Built for the modern enterprise architecture An intelligent, integrated, and scalable solution to protect your business-critical web applications from malicious attacks, with no changes to your existing infrastructure. View product Akamai Web Application Protector Web Application Firewalls (WAF) by Akamai Technologies Web Application Protector is designed to meet the needs of enterprises to easily protect web assets from web application attacks and DDoS attacks with much less maintenance than traditional firewalls. View product Imperva Web Application Firewall (WAF) Web Application Firewalls (WAF) by Imperva Imperva's Web Application Firewall (WAF) provides out-of-the-box security for your web applications. It detects and prevents cyber threats, ensuring seamless operations and peace of mind. Protect your digital assets with Imperva's robust, industry-leading solution. Awards: Imperva has been recognized as a 7-time Leader in the Gartner Magic Quadrant for Web Application Firewalls. View product Advanced API Security Web Application Firewalls (WAF) by Wallarm: API Security Leader Wallarm is the platform Dev, Sec, and Ops teams choose to build cloud-native APIs securely, monitor them for modern threats, and get alerted when threats arise. View product Radware Cloud WAF Web Application Firewalls (WAF) by Radware Radware’s Cloud WAF Service is a web application firewall that provides continuous adaptive web application security protection and full coverage of OWASP Top 10 threats. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights Alibaba Web Application Firewall Web Application Firewalls (WAF) by Alibaba Cloud Web Application Firewall (WAF) protects your website servers against intrusions, detects and blocks malicious traffic directed to your websites and applications. View product DNSFilter Web Application Firewalls (WAF) by DNSFilter DNSFilter protects every click, leveraging AI-driven content filtering and threat protection to block threats 10 days earlier than competitors and secure users everywhere they work. View product AppTrana WAAP Web Application Firewalls (WAF) by Indusface AppTrana WAAP - A unified platform to discover, protect, and monitor your public websites & APIs in real time. 1. Discover all public IPs, apps, sub-domains, websites and other assets 2. Scan websites, APIs and mobile apps for vulnerabilities and malware 3. Protect websites and APIs from vulnerability, DDoS, and bot attacks 4. Monitor anomalies in site traffic and take preventive actions View product Medianova WAF Web Application Firewalls (WAF) by Medianova Protect Your Web Application and APIs with Medianova WAF without Compromising performance Types of Attacks We Protect You From SQL Injection Cross-Site Scripting (XSS) Local File Inclusion Remote File Inclusion PHP Code Injection Java Code Injection Shellshock Unix/Windows Shell Injection and more. Security at The Edge Extend your security perimeter and block attacks at the edge, before they ever reach the origin. Improve your defense with Medianova WAF, which runs on our powerful global edge network that is distributed among 50+ data centers. Managed Rulesets & Customized Rules Protect your Apps and APIs against sophisticated attacks reported by OWASP “Top 10 Security Risks” list, such as Cross-Site-Scripting (XSS) and SQL Injection. Define customized rules for tailored protection and prevent false-positives. Continuous Update of WAF Rulesets Maintain effective protection against emerging threats and vulnerabilities. View product Drupal Steward Web Application Firewalls (WAF) by Drupal Association Drupal Steward is a web application firewall that bridges the gap between the time when a security release is announced and when your site is fully updated with the new security patch. This globally distributed service from the Drupal Security Team and the Drupal Association provides immediate, affordable protection for your website, while giving your IT team the flexibility to implement site updates without disrupting other priorities. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:16 |
https://huggingface.co/datasets/OpenDataArena/ODA-Mixture-100k | OpenDataArena/ODA-Mixture-100k · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: OpenDataArena / ODA-Mixture-100k like 90 Follow OpenDataArena 49 Modalities: Text Formats: parquet Size: 100K - 1M ArXiv: arxiv: 2512.14051 Libraries: Datasets Dask Polars + 1 License: apache-2.0 Dataset card Data Studio Files Files and versions xet Community = 10, then there is a carry. So, 2X + 1 >= 10 => X >= 4.5. Since X is an integer digit, X >= 5. So, if the digit before the trailing 9s is 5 or more, then adding that digit in n and n+1 will result in a carry.\n\nWait, that's an important point. So, when adding n and n+1, the only digit that can cause a carry is the digit that gets incremented when moving from n to n+1 (i.e., the first non-9 digit from the right). All other digits either add 9 + 0 = 9 (no carry) or the same digit in both numbers (if no trailing 9s). Wait, but if there are no trailing 9s, then n+1 is just n with the last digit incremented. For example, n = ABCD, n+1 = ABC(D+1). Then, adding n and n+1 would have the last digit as D + (D + 1) = 2D + 1. Similarly, the other digits are A + A, B + B, C + C. Wait, no: actually, n and n+1 differ only in the last digit if there are no trailing 9s. So, for example, n = 1234, n+1 = 1235. Then, adding them:\n\n1+1=2 (thousands), 2+2=4 (hundreds), 3+3=6 (tens), 4+5=9 (units). So, units digit is 4 + 5 = 9, others are same digits added together. Wait, no: wait, in n = 1234, the thousands digit is 1, hundreds 2, tens 3, units 4. In n+1 = 1235, thousands, hundreds, tens are the same, units is 5. So adding n and n+1:\n\nThousands: 1 + 1 = 2\nHundreds: 2 + 2 = 4\nTens: 3 + 3 = 6\nUnits: 4 + 5 = 9\nSo, all digits except the units are just double the original digits. But the units digit is 4 + 5 = 9. So, in this case, there's no carry. But if the units digit in n is 5, then n+1 has units digit 6, and adding them gives 5 + 6 = 11, which would carry over.\n\nWait, so in general, when adding n and n+1, the only digit that can cause a carry is the digit where the increment happens. If that digit in n is 5 or higher, then adding it to the next digit (which is one higher) will result in a carry. If the digit is 4 or lower, adding it to the next digit (which is one higher) won't cause a carry. For example:\n\n- If the units digit is 4: 4 + 5 = 9 (no carry)\n- If units digit is 5: 5 + 6 = 11 (carry)\n\nSimilarly, if the tens digit is being incremented (because the units digit was 9), then:\n\nn = ...X9, n+1 = ...(X+1)0. Adding them:\n\n...X9 + ...(X+1)0:\n\nDigits: For the tens place: X + (X + 1) = 2X + 1. If 2X + 1 >= 10, then carry. So, again, if X >= 5, carry occurs.\n\nSimilarly, if the hundreds digit is being incremented (because the tens and units were 99):\n\nn = ...Y99, n+1 = ...(Y+1)00. Adding them:\n\n...Y99 + ...(Y+1)00:\n\nHundreds place: Y + (Y + 1) = 2Y + 1. If 2Y + 1 >= 10, carry. So Y >= 5 causes a carry.\n\nSame for thousands place. For example, n = 1999, n+1 = 2000. Adding them:\n\n1 + 2 = 3 (thousands place)\n9 + 0 = 9 (hundreds)\n9 + 0 = 9 (tens)\n9 + 0 = 9 (units)\nNo carry, since 1 + 2 = 3 = 10, then a carry occurs. Therefore, even if the thousands digit A is 5, then 2A = 10, which would cause a carry. Wait, but A is the thousands digit. In our problem, A can be 1 or 2 (since the numbers are from 1000 to 2000). So, 2A would be 2 or 4, which are both less than 10. So, in our specific case, since the thousands digit is 1 or 2, 2A is 2 or 4, so no carry from the thousands place.\n\nBut wait, in the problem, we're adding numbers from 1000 to 2000. So, the thousands digit is 1 for all numbers except 2000, which has 2. So, when adding n and n+1, both numbers will have thousands digit 1, except when n = 1999 and n+1 = 2000. In that case, n = 1999 (thousands digit 1) and n+1 = 2000 (thousands digit 2). So adding those thousands digits: 1 + 2 = 3, which is less than 10, so no carry.\n\nTherefore, in our problem, the thousands digit addition will never cause a carry, because either 1 + 1 = 2 (for numbers from 1000 to 1998 and their consecutive pairs) or 1 + 2 = 3 (for the pair 1999 + 2000). So, the thousands place is safe.\n\nTherefore, the possible carries can only come from the hundreds, tens, or units places. Let's consider different scenarios based on where the increment occurs when moving from n to n+1.\n\nCase 1: The units digit is not 9. Then, n+1 is n with units digit incremented by 1. So, adding n and n+1, the units digits are D and D + 1. So, sum in units place: D + (D + 1) = 2D + 1. For there to be no carry, 2D + 1 D = 11, which causes a carry.\n\nBut wait, in our problem, if the units digit is not 9, then we increment the units digit. So, in this case, the only digit that changes is the units digit. Therefore, when adding n and n+1, the thousands, hundreds, and tens digits are the same in both numbers, so adding them would be 2A, 2B, 2C (which, as we saw, A is 1 or 2, so 2A is 2 or 4, which is safe; B and C can be 0-9, so 2B and 2C could be up to 18. Wait, hold on! Wait, if we are adding n and n+1 where only the units digit is changing, then actually, in the thousands, hundreds, and tens places, the digits in n and n+1 are the same. Therefore, when adding n and n+1, in the thousands place, it's A + A = 2A. Similarly for hundreds and tens places. So, for example, if n is 1234, then n+1 is 1235. Adding them:\n\nThousands: 1 + 1 = 2\n\nHundreds: 2 + 2 = 4\n\nTens: 3 + 3 = 6\n\nUnits: 4 + 5 = 9\n\nSo, all digits except units are doubled. Therefore, even if B or C is 5, then 2*5 = 10, which would cause a carry. Wait, that's a problem. Wait, in this case, even if the units digit is fine (e.g., D=4), but if another digit (like B or C) is 5 or more, then doubling it would result in 10 or more, hence a carry. But wait, the problem states \"no carrying required when the two integers are added\". So, even if a carry is caused by the hundreds or tens place, that pair is excluded.\n\nTherefore, my previous reasoning was incorrect. I had only considered the digit where the increment occurs, but actually, when adding n and n+1, all digit pairs are added, and if any of them (except the one that increments) sum to 10 or more, there's a carry. So, for example, if n has a hundreds digit of 5, then in n and n+1, the hundreds digits are both 5, so adding them gives 10, which is a carry. Therefore, such a pair would require carrying.\n\nWait, that complicates things. So, in order for the addition of n and n+1 to not require any carrying, all digit pairs (thousands, hundreds, tens, units) must sum to less than 10. But when adding n and n+1, since n+1 is formed by incrementing n by 1, the digits of n and n+1 can differ in more than one place if there are trailing 9s.\n\nWait, let me think again. For a number n, n+1 is formed by incrementing the last digit by 1, unless that digit is 9, in which case it rolls over to 0 and the next digit is incremented, and so on. Therefore, except for the digits that are rolled over from 9 to 0, all other digits remain the same. The first non-9 digit from the right is incremented by 1.\n\nTherefore, when adding n and n+1, the digits that are rolled over (from 9 to 0) will be added as 9 + 0 = 9 (no carry). The first non-9 digit from the right in n is incremented by 1 in n+1. All digits to the left of that remain the same. Therefore, when adding n and n+1:\n\n- For digits that were rolled over (i.e., trailing 9s in n): 9 + 0 = 9 (no carry)\n- For the first non-9 digit from the right in n: let's say it was D, then in n+1 it is D + 1. So, sum is D + (D + 1) = 2D + 1. If this is >=10, carry occurs.\n- For digits to the left of that: they are the same in n and n+1, so sum is 2*D. If 2*D >=10, carry occurs.\n\nTherefore, in order for the addition of n and n+1 to require no carrying, all the following must be true:\n\n1. For the digit where the increment occurs (the first non-9 digit from the right in n): 2D + 1 D =10)\n2. For all digits to the left of the incremented digit: 2*D D =10)\n3. For all digits that are rolled over (trailing 9s in n): 9 +0=9 which is okay.\n\nTherefore, in order for the addition n + (n+1) to not require carrying, the following must hold:\n\n- The first non-9 digit from the right in n must be D X Y Z X Y =10)\n- The hundreds digit X must be X P0: has 4 faces. Step1: adds 4 tetras. Step2: now, P1 has how many faces?\n\nEach original face (4) leads to???? Original faces: 4. Each being subdivided such? After adding tetrahedrons, new faces generated as.... In Pi+1, the number of faces is 16.\n\nBut actually, when adding a tetrahedron to a face:\n\nOriginal face: 1 triangle. Replace midpoint triangle with a tetra. So left withOriginal face split into three triangles. The added tetra has three new faces (the other sides).\n\nThus after step: for each face in Pi, Pi+1 face count is 3* (original face splits) plus 3*new faces.\n\nTherefore, the number of faces at each step Qi+1= 3*Qi + 3*Qi =6*Qi.\n\nWait, substituting that, for Pi's Q: If start with Q0=4, next Q1=6*4=24?\n\nWait maybe earlier Step1: start with four faces.\n\nEach face generates three faces from the original splits (the non-replaced parts) and three faces from the added tetrahedron, totaling 6 per face. Thus, Q1=4*6=24.\n\nThen Q2 would be Q1 multiplied by 6: 24*6=144. Similarly Q3=144*6=864. So Qi=4*6^i.\n\nBut the problem ends with P3, the volume up to third iteration.\n\nAlternatively, think in terms for the V. Volume at step0: Vi=1. Step1 added F0=4*V/8=0.5. So Vi+1=Vi + added.\n\nWhat happens empirically at Step0: V0=1\n\nS1: a1 =1 + number_of_faces(P0)*added_volume. Where number_of_faces(P0) =4, and added_volume is 1/8\n\nSo total added_bv1=4*1/8=1/2 =>V1=1+0.5=1.5\n\nNow the polyhedronP1 has number_of_faces S'1=24\n\nSo, moving to V2, adds number_of_faces(P1)*added_volume_p2. But added_volume_p2 is?\n\nHowever, each face of P1 is smaller? Each face of Pi+1 have edge lengths?\n\nWait, but in Pi, the added tetrahedrons at each step may varies sizes.\n\nFor example, in P0, edge length L. The added tetrahedron's edge length is L/2. When you then move to step1, in P1, faces are (for original parts) Those remaining on replaced faces, or from the added tetrahedrons.\n\nEach new face added in step1 is the three fresh face's of the tetrahe'drons. These three new faces are part of added tetraherons with edge length L/2.\n\nAt S1, the polyhedron P1 has:\n\nOriginal four tetrahedron's faces but each replaced into three subfaces. Each subface has edge length L/2 (since midpoints splits edges into halves). Because original edges of P0 was L, so after splitting into subfaces (the non-replaced outer triangles) each edge is (along original edges)→split between edges, which were at L, but the length between the midpoints would be L/2.\n\n Therefore, the original (remaining) subfaces after replacement in P0→P1 are triangles with edge length L/2.\n\nSo for S1’s faces: the original split faces and the new faces from the added tetrahedrons:\n\nP1's faces are two types:\n\n1. Residual subdivided faces from P0, which are triangles with edge length L/2, and;\n\n2. The three new faces from each added tetrahedron in P0→P1, whose edge length are also half (L/2).\n\nTherefore, all faces of S1 have edge length L/2. So, in proceeding Step2, Vi+1= Vi +Faces(P_i)*V_added.\n\nIn steps:\n\nStep0: V =1, Faces=4.\n\nStep1: V =1 +4*(1/8) =1 +0.5=1.5. Faces=4* (if Q increases to twofold), but actually according to previous, Faces=S1=24?\n\nWait, hold a horse! P1's Faces:\n\nFor original 4 faces in P0: Each face initially comprises retaining three residual subfaces (each edge length L/2) and three new faces from the added tetra. Each of these new tetra's non-base faces are also of edge length L/2, since the added tetra is edge length L/2.\n\nHence, each replaced face in P0 spawned 3 residual subfaces and 3 new faces. Therefore, total per original face:6 new faces.\n\nBut axially, So Faces of P1:4 original faces *6 =24。\n\nThus S1 has 24 faces, each edge length L/2. Similarly, in moving to S2, each face @ L/2 will have their midpoint triangle replaced by a tetrahedron with edge length (L/2)/2=L/4, each i volume will be= [ (L/4)^3*sqrt(2)/12] = [L^3*sqrt(2)/12 ]*(1/64 )= V0/64, since L^3*sqrt(2)/12=1.\n\nHence, each added tetrahedroni volume on stepier Step2 is 1/64.\n\nThen total added �Volume in step2 is faces(P1)*added_volume=24* (1/64)=24/64=3/8. Hence V2= V1 +3/8=1.5 +0.375=1.875=15/8.\n\nProceeding to Step3:\n\nIn step2, P2 has Faces=Q2= Faces(P1)*6=24*6=144, each with edge length L/4. The added tetrahedron volume each would be(1/8)^3 iteration-wise. Wait explicitty.\n\nBut after two reproductions: each added tetra in step 2 has edge length L/4, therefore Vol=1/64=1/(8^2), since initial L, step1 L/2 step2 L/4 etc. So volumetric scaling by 1/8 here each time.\n\nBut for step3: added volume(Faces(P2))*(1/(8^3)).\n\nWait. Previously:\n\nStep0: added_tetra=1/2 (4*(1/8))\n\nStep1: added=3/8 (24*(1/64)).Wait 1/8 was step1 Sized added?\n\nOr recognition that te Steps n added volumeS(faces(Number) * V(added each). at each step the faces multiply by 6, and the volume added per being (1/8)* (1/8)} of the previous added's volume.\n\nWait contrariwise, the faces multiply by 6, but the added virtues each Tagg'sigo te multiplier of 1/8 the prior volume.\n\nWait perhaps volume added_i= (prev Faces) *vol add'sii.\n\n volume add at step K: F_{k-1} * (1/8)^{k}\n\nWait moreprecisely, at each step k:\n\n volume_added_k= F_{k-1} * ( (1/2)^3 ), as the edge length scaling with 1/2 each time, per iteration.\n\nBut (1/2)^3=1/8, and weighted by F_{k-1}.\n\nButhow k’}— F_{0}=4,\n\n volume_added_1: 4*(1/8)=0.5,\n\n F_{1}=24,\n\n Volume_added_2:24/(8=24*(1/8)=3,\n\n But if at step2,_F1 that Faces are original of edge_length L/2, per tetra result in added tetrahedrons with their volumen (Lface edge /2)^3 indexes.\n\n Alternatively:\n\n conclusively, each additional tetra at stepk indexWith their edge_length equal to half the current'attuale step edge length. And Vol is, sinceovariano edge-length cubed: at stepk, edge_length= L/(2^k) and ergo the tetraVol av i wasV0/(8^k). Since V0=1, Vol_add por added tetra=1/(8^k).\n\n Thence, the number of TAg. etáleur_o stepék=F_{k-1}\n\n Thus volume_added due to pi o------------ to:\n\n V_total= V0 + Σ_{k=1}^inftyF_{k-1} * 1/(8^k) |\n\nBut since aim's os Vol to find V_due Till P3: thus oh for steps'reldom up to 3,\n\n V3= V0 + added_1Σ, added_2, added_3.\n\n F_{0}=4\n\n added_1=4*(1/8)=0.5\n\n F_{1}=4*6=24\n\n added_2 =24*(1/8^2)=24/64=0.375=3/8.\n\n F2=24*6=144.\n\n added_3=144*(1/8^3)=144/(512)= 0.28125=9/32.\n\n Consequently, V3=1 + 0.5 +0.375 +0.28125=1 + 0.5 i =1.5 +0.375=1.875 +0.28125=2.15625\n\n.\n\n2.15625 can be t+ turns to fraction.\n\nSince *t is equal to 9/32; let me repress this:\n\nV3=1 (step0) +4*(1/8) =1 +1/2=3/2 (step1) ? V1 = 3/2\n\nV2=3/2 + 24*(1/(8^2))=3/2 +24/64=3/2 +3/8= (12/8 +3/8)=15/8\n\nV3=15/8 +144/512. One thousand144/512=144 divided512 simplifies 144 /512=9/32 ?\n\nYes, 144/512 = (144 ÷16)=9, 512 ÷16=32, so 9/32.\n\nHence, V3=15/8 +9/32.\n\nConvert to common denominator:\n\n15/8=60/32.\n\n60/32 +9/32=69/32.\n\nTherefore, V3=69/32. But 69 and 32. Are they coprime? Explain si32'eese?\n\n69 factors:3×23. 32=2⁵\n\n They share no common factors, yes.\n\nSo m/n=69/32. n + m=69+32=101.\n\nBut why?\n\nWait but previous calculation.\n\n each added step:\n\nStep_k:\n\nAdded volumen = number of Faces in Pi_{k-1} * (1/8)^ ?\n\nWait Vi=1, then V1=1 +4*(1/8)=1 +0.5=1.5.\n\nQ1_faces=6*4=24.\n\nV2=1.5 +24*(1/8)^2=24*(1/64)=0.375=1.5+0.375=1.875=15/8。\n\nFaces_Q2= 24*6=144。\n\nV3=15/8 +144*(1/8)^3=144*(1/512 )=(144/512)=3*(48)/s→144 divided by 512:\n\n144 ÷16=9,512 ÷=32。144=9*16 ; 512=32*16. So gcd=16; simplify to9/32.\n\nTherefore V3=15/8 +9/32=60/32 +9/32=69/32.\n\nAnd69 and32，primeitatively, they have no common factors other than?\n\n32 is 2^5，69= 3*23，wellnone factors. so YES, coprime.\n\n thus m +n=69+32=101.\n\n This is the correct answer, I might be summarized tidily. Therefore,101。\n\n**Final Answer**\n\\boxed{101}"}}},{"rowIdx":3,"cells":{"id":{"kind":"number","value":3,"string":"3"},"source":{"kind":"string","value":"LIMO"},"instruction":{"kind":"string","value":"Set $A$ consists of $m$ consecutive integers whose sum is $2m,$ and set $B$ consists of $2m$ consecutive integers whose sum is $m.$ The absolute value of the difference between the greatest element of $A$ and the greatest element of $B$ is 99. Find $m.$"},"response":{"kind":"string","value":"Okay, so I need to solve this problem where there are two sets, A and B. Set A has m consecutive integers, and their sum is 2m. Set B has 2m consecutive integers, and their sum is m. The absolute difference between the greatest elements of A and B is 99. I have to find m. Hmm, let's break this down step by step.\n\nFirst, let me recall that the sum of consecutive integers can be found using the formula for an arithmetic series. The sum of n consecutive integers starting from a is given by n/2 * [2a + (n - 1)d], where d is the common difference. But since they are consecutive integers, d = 1. So the formula simplifies to n/2 * [2a + (n - 1)]. \n\nAlternatively, since the numbers are consecutive, the average of the series is the middle term, which is also the average of the first and last term. So the sum can be thought of as the average multiplied by the number of terms. That might be an easier way to approach it.\n\nLet me start with set A. It has m consecutive integers, and the sum is 2m. Let's denote the first term of set A as a. Then the terms are a, a+1, a+2, ..., a + (m - 1). The sum of these terms is the number of terms times the average of the first and last term. So sum = m * [(a + (a + m - 1)) / 2] = m * (2a + m - 1)/2. According to the problem, this sum is 2m. So:\n\nm * (2a + m - 1)/2 = 2m\n\nLet me simplify this equation. Multiply both sides by 2:\n\nm * (2a + m - 1) = 4m\n\nDivide both sides by m (assuming m ≠ 0, which is reasonable since m is the number of terms in set A):\n\n2a + m - 1 = 4\n\nNow solve for a:\n\n2a = 4 - m + 1\n2a = 5 - m\na = (5 - m)/2\n\nSo the first term of set A is (5 - m)/2. Since the elements are integers, a must be an integer. Therefore, (5 - m) must be even, so 5 - m is even ⇒ m is odd. So m is an odd integer. That's useful information.\n\nNow, the greatest element of set A is a + m - 1. Plugging in a:\n\nGreatest element of A = (5 - m)/2 + m - 1 = (5 - m)/2 + (2m - 2)/2 = (5 - m + 2m - 2)/2 = (m + 3)/2\n\nSo the greatest element of A is (m + 3)/2. That simplifies things.\n\nNow moving on to set B. Set B has 2m consecutive integers with a sum of m. Let's denote the first term of set B as b. Then the terms are b, b+1, ..., b + (2m - 1). The sum of these terms is 2m * [(b + (b + 2m - 1))/2] = 2m * (2b + 2m - 1)/2 = m * (2b + 2m - 1). The problem states that this sum is m. So:\n\nm * (2b + 2m - 1) = m\n\nAgain, assuming m ≠ 0, divide both sides by m:\n\n2b + 2m - 1 = 1\n\nSolve for b:\n\n2b = 1 - 2m + 1\n2b = 2 - 2m\nb = (2 - 2m)/2 = 1 - m\n\nSo the first term of set B is 1 - m. Therefore, the greatest element of set B is b + 2m - 1 = (1 - m) + 2m - 1 = (1 - 1) + (2m - m) = m. So the greatest element of B is m.\n\nNow, according to the problem, the absolute difference between the greatest elements of A and B is 99. So:\n\n| (m + 3)/2 - m | = 99\n\nLet me compute this expression inside the absolute value:\n\n(m + 3)/2 - m = (m + 3 - 2m)/2 = (-m + 3)/2\n\nSo | (-m + 3)/2 | = 99\n\nMultiply both sides by 2:\n\n| -m + 3 | = 198\n\nWhich is equivalent to:\n\n| 3 - m | = 198\n\nSo, 3 - m = 198 or 3 - m = -198\n\nSolving for m:\n\nCase 1: 3 - m = 198 ⇒ -m = 195 ⇒ m = -195\n\nBut m is the number of terms in set A, which must be a positive integer. So discard this solution.\n\nCase 2: 3 - m = -198 ⇒ -m = -201 ⇒ m = 201\n\nSo m = 201. Let me verify if this is valid.\n\nFirst, check the first term of set A: a = (5 - m)/2 = (5 - 201)/2 = (-196)/2 = -98\n\nSo set A starts at -98 and has 201 consecutive integers. The greatest element of A is (m + 3)/2 = (201 + 3)/2 = 204/2 = 102. Wait, but if the first term is -98 and there are 201 terms, the last term is -98 + 200 = 102. That matches.\n\nSum of set A: The average is ( -98 + 102 ) / 2 = 4/2 = 2. Number of terms is 201. So sum is 2*201 = 402. Which should be equal to 2m = 2*201 = 402. Correct.\n\nNow set B: first term is 1 - m = 1 - 201 = -200. Number of terms is 2m = 402. The last term is -200 + 401 = 201. So the greatest element of B is 201. The absolute difference between 102 and 201 is |102 - 201| = 99. Which is as per the problem. So this checks out.\n\nBut wait, the problem says the absolute difference between the greatest elements of A and B is 99. The greatest element of A is 102, of B is 201. 201 - 102 = 99. So that's correct.\n\nTherefore, m = 201. So the answer is 201. Hmm, but let me check if I did everything correctly.\n\nWait, let me re-examine the steps. For set A, the greatest element was calculated as (m + 3)/2, which for m=201 gives (201 + 3)/2 = 204/2 = 102. Then set B's greatest element is m=201, which is 201. The difference is 201 - 102 = 99. So absolute value is 99. Correct.\n\nBut wait, in the problem statement, set B has 2m consecutive integers. When m=201, set B has 402 terms. Starting at 1 - 201 = -200, so terms from -200 to 201 inclusive. Let's check the sum. The sum of numbers from -200 to 201. Wait, how many terms are there? From -200 to 201 inclusive, that's 201 - (-200) + 1 = 201 + 200 +1 = 402 terms. Correct. The sum can be calculated as (number of terms)/2 * (first term + last term) = 402/2 * (-200 + 201) = 201 * 1 = 201. But the sum is supposed to be m, which is 201. So that's correct.\n\nTherefore, all conditions are satisfied. So m=201 is indeed the correct answer.\n\nBut let me just check if there are any other possible solutions. The absolute value equation |3 - m| = 198 gave us m=201 and m=-195, but m must be positive. So only m=201. So that's unique.\n\nTherefore, the answer is 201.\n\n**Final Answer**\n\\boxed{201}"}}},{"rowIdx":4,"cells":{"id":{"kind":"number","value":4,"string":"4"},"source":{"kind":"string","value":"LIMO"},"instruction":{"kind":"string","value":"Let $S$ be the set of all positive rational numbers $r$ such that when the two numbers $r$ and $55r$ are written as fractions in lowest terms, the sum of the numerator and denominator of one fraction is the same as the sum of the numerator and denominator of the other fraction. The sum of all the elements of $S$ can be expressed in the form $\\frac{p}{q},$ where $p$ and $q$ are relatively prime positive integers. Find $p+q.$"},"response":{"kind":"string","value":"Okay, so the problem is about finding all positive rational numbers r such that when you write r and 55r as fractions in their lowest terms, the sum of the numerator and denominator of one is equal to the sum of the numerator and denominator of the other. Then we need to find the sum of all these r and express it as p/q with p and q coprime, then give p+q.\n\nHmm. So, first, let me understand what this means. Let's take a rational number r, which can be written as a/b in lowest terms, meaning that a and b are coprime positive integers. Similarly, 55r would be written as (55a)/b, but since it's in lowest terms, we need to divide 55a and b by their greatest common divisor. So, 55r would be (55a/gcd(55a, b)) / (b/gcd(55a, b)).\n\nThe problem states that the sum of the numerator and denominator of one of these fractions equals the sum for the other. So, either a + b equals the numerator of 55r plus its denominator, or vice versa. That is, either:\n\na + b = (55a/gcd(55a, b)) + (b/gcd(55a, b))\n\nor\n\n(55a/gcd(55a, b)) + (b/gcd(55a, b)) = a + b\n\nSo, that's equivalent to saying:\n\nEither the sum for r is equal to the sum for 55r, or their sums are equal. But since equality is symmetric, it's just one condition: the two sums must be equal. So, the idea is that when simplifying both r and 55r, the sum of numerator and denominator for each, in their reduced forms, must be the same.\n\nSo, how can we approach this? Let's denote r as a/b in lowest terms. So, a and b are coprime. Then, 55r is 55a/b. Let's call the reduced form of 55a/b as c/d, where c and d are coprime. Then, we must have that a + b = c + d. Or c + d = a + b. But since they are sums, it's the same. So, we can say that the sum a + b must equal the sum c + d.\n\nSo, perhaps, need to set up equations for this. Let me think.\n\nSince c/d is the reduced form of 55a/b, gcd(55a, b) must divide both 55a and b. Therefore, gcd(55a, b) is gcd(55, b) since a and b are coprime.\n\nWait, let me check that. Since a and b are coprime, then gcd(55a, b) = gcd(55, b) because any common divisor of 55a and b must divide both 55a and b, but since a and b are coprime, the divisor must divide 55 and b.\n\nYes, that's correct. So that gcd(55a, b) = gcd(55, b). Therefore, the numerator and denominator of 55r are 55a divided by gcd(55, b) and b divided by gcd(55, b). Hence:\n\nNumerator: 55a / gcd(55, b)\nDenominator: b / gcd(55, b)\nSo, c = 55a / g, d = b / g, where g = gcd(55, b)\n\nTherefore, c + d = (55a + b) / g\n\nTherefore, the condition is that a + b = (55a + b) / g, where g = gcd(55, b)\n\nSo, let’s write down the equation:\n\na + b = (55a + b)/g\n\nMultiply both sides by g:\n\ng(a + b) = 55a + b\n\nWhich is:\n\nga + gb = 55a + b\n\nRearranged:\n\n(ga - 55a) + (gb - b) = 0\n\na(g - 55) + b(g - 1) = 0\n\nSo,\n\na(55 - g) = b(g - 1)\n\nWait: When moved the terms:\n\na(g - 55) + b(g - 1) = 0 → a(55 - g) + b(1 - g) = 0 ?\n\nHmm, maybe better to rederive the equation.\n\nStarting from:\n\ng(a + b) = 55a + b\n\nSo,\n\ng a + g b = 55a + b\n\nThen grouping terms:\n\ng a -55a = b - g b\n\nWhich is:\n\na(g - 55) = b(1 - g)\n\nMultiply both sides by -1:\n\na(55 - g) = b(g - 1)\n\nSo,\n\na(55 - g) = b(g - 1)\n\nSo, let's note that here, g is the gcd(55, b), which divides 55. So g is a divisor of 55, which can be 1, 5, 11, or 55.\n\nTherefore, possible values of g: 1,5,11,55. So, we can consider each value of g, then obtain equations relating a and b, given that a/b is in lowest terms (so a and b are coprime).\n\nOur main equation is a(55 - g) = b(g - 1)\n\nLet’s consider each possible g.\n\nCase 1: g = 1 (gcd(55, b) =1)\n\nThen,\n\na(55 -1)= b(1 -1) → a(54)=b(0) → 54a=0. But a is positive integer, so this is impossible. Therefore, there's no solution when g =1.\n\nCase 2: g =5 (gcd(55, b)=5)\n\nThen,\n\na(55 -5)=b(5 -1) → a*50=b*4 → 50a=4b → 25a=2b\n\nSo, 25a=2b ⇒ b = (25a)/2. Since b must be integer, so a must be even. Let a=2k, then b=(25*2k)/2=25k.\n\nBut since a and b must be coprime. Let a =2k and b=25k. Then gcd(2k,25k)=gcd(2,25)*k=1*k, but k must divide both 2k and 25k. So, to ensure that gcd(a, b)=1, we need k=1. Because if k >1, then gcd(2k,25k)=k, which must be 1. Therefore k=1.\n\nThus, the only possible a and b in this case are a=2*1=2, b=25*1=25.\n\nSo, checked gcd(2,25)=1, correct.\n\nThus, when g=5, the fraction r is a/b=2/25.\n\nNow let's verify:\n\nOriginal r=2/25, which is in lowest terms. 55r=55*(2)/25=110/25=22/5 in reduced terms. Wait, 110/25 simplifies to 22/5, correct. The sum of numerator and denominator for r is 2+25=27; sum for 55r is 22+5=27. So, yes, both sums are equal. So this is a valid solution.\n\nCase 3: g=11. Then, equation becomes:\n\na(55 -11)=b(11 -1) → a*44=b*10 → 44a=10b → 22a=5b.\n\nThus, 22a=5b. Then, since a and b must be coprime here (for r=a/b to be in lowest terms), we have:\n\n22a=5b -> b=(22/5)a. But a and b are integers, so a must be divisible by 5. Let a=5k, then b=(22/5)*5k=22k.\n\nThus, a=5k, b=22k. Then, gcd(a, b)=gcd(5k,22k)=gcd(5,22)*k=1*k=k. So, for a/b to be reduced, we need k=1, so that gcd(5k,22k)=k=1. Hence, the only solution here is a=5, b=22.\n\nCheck gcd(5 and 22)=1, yes. Compute r=5/22. Now, 55r=55*(5)/22=275/22 reduces to 25/2 (275 divided by 22: divide both by gcd(275,22). gcd(275,22). Let me compute: 275 is divisible by 5? 275=5×55, 22 is 2×11. GCD(5×55,2×11). The common divisors? 55 and 22 have gcd 11. Wait, 275=5*55=5*5*11, 22=2*11. So gcd is 11. Thus 275/22 reduces to (275/11)/(22/11)=25/2. Sum numerator and denominator for 5/22 is 5+22=27. For 25/2 it's 25+2=27. Correct. So indeed, another solution.\n\nCase 4: g=55 (gcd(55, b)=55). Then,\n\nequation:\n\na(55-55)=b(55-1) → a*0= b*54 → 0=54b. Since b is positive integer, no solution. So, no case here.\n\nSo, possible solutions only occur when g=5 and g=11, each giving one rational number: r=2/25 and r=5/22. So, the set S has elements 2/25 and 5/22. So, sum of all elements would be 2/25 +5/22.\n\nTo compute this, let's get denominator LCM of 25 and 22. 25 is 5², 22 is 2×11. So LCM is 2×5²×11=550. So 2/25 = 44/550 and 5/22=125/550. Adding them gives 44+125=169. Then, 169/550. Then and check how's 169 and 550 related.\n\nGCD of 169 and 550. 169 is 13², 550 is 2×5²×11. They share no common prime factors. So yes, 169/550 is the reduced form. So p=169, q=550, therefore p+q=169+550=719.\n\nWait, but hold on. Let me cross check all steps.\n\nSolution when g=5: a=2, b=25? Sum 2+25=27. 55r=110/25 reduce to 22/5, sum 22+5=27. Good.\n\nSimilarly, case g=11: a=5, b=22. Sum same too. So both fractions 2/25 and 5/22 are in S. Are there other fractions?\n\nWait, I only found two elements in S. Is that all?\n\nBut let me think again. When we solved for each case (g=5 and 11), under the equation:\n\na(55 -g)=b(g -1).\n\nIn each case, we considered g=5 and derived a=2, b=25. For g=11, a=5, b=22.\n\nBut maybe there is an assumption here. Because In the equation, after setting 25a=2b when g=5, we see that since 25 and 2 are coprime, the minimal solution is a=2, b=25. Then equations: k.\n\nBut maybe are there other solutions where a and b are multiples by coprime.\n\nWait. Let me recheck for the case of g=5:\n\nWe had 25a=2b ⇒ 25a =2b ⇒ a=2k, b=25k. But since gcd(a,b)=1 implies gcd(2k,25k)=k. So for them to be coprime, k must be 1. So only possible solution is a=2, b=25.\n\nSame for case g=11:\n\n22a=5b ⇒ (gcd terms etc) a=5k, b=22k ⇒ gcd(a,b)=k. Need k=1, so a=5, b=22.\n\nTherefore, only two solutions. So sum is 2/25 +5/22.\n\nCompute that sum. Converting 2/25 into 44/550 (25×22=550), and 5/22 is 125 (5×25=125)/550? Wait, no. Wait, converting 2/25 to fractions with denominator 550 (LCD of 25 and 22):\n\n25=5², 22=2×11, LCM is 5²×2×11=550.\n\nSo 2/25 = (2×22)/(25×22)=44/550.\n\n5/22=(5×25)/(22×25)=125/550.\n\n44 +125=169. So total 169/550.\n\n169 and 550: reduced? GCD(169,550). Divisors of 169: 13². 550:55×10=5×11×2×5. So, no common factors. So yes, 169/550 reduced. So p=169, q=550, sum p+q=719.\n\nBut wait, the answer description says \"The sum of all the elements of S can be expressed in the form p/q, where p and q are relatively prime positive integers. Find p+q.\" So answer should be 719.\n\nBut hang on, but let's check again.\n\nIs S only the two elements 2/25 and 5/22? Let me make sure if we haven't missed possibilities.\n\nSuppose, perhaps, there could be more fractions, for example where or fractions where numerator and denominator have other divisors.\n\nBut given how we broke down the problem, since gcd(55, b) can only be 1,5,11, or 55, which are divisors of 55. For each possible gcd, we have:\n\nIf gcd=5, gives one solution,\n\ngcd=11 gives another,\n\nwith gcd=1 and 55 yielding no solutions.\n\nThus only two solutions.\n\nHence sum is 2/25 +5/22=169/550, p+q=719.\n\nSo unless there's another approach where more solutions exist.\n\nAlternatively, let me assume that maybe there's a fraction where r and 55r have same sum. So alternative approach:\n\nLet r=a/b, reduced. Then 55r =c/d, reduced. Then a + b = c + d.\n\nFrom 55r=c/d ==> 55 a/b = c/d. So 55a d = c b. Since c and d are coprime, because reduced fraction.\n\nBut r=a/b is also reduced. So possible relationships.\n\nHmm, but 55a/b = c/d, which implies that c/d=55a/b --> cross multiply: 55a d = c b\n\nBut c and d are coprime, therefore the divisors... Perhaps can model this equation? But since you cross multiply, it's 55a*d = c*b. Then whether can represent the mapping between a,b,c,d.\n\nBut maybe not too useful compared to prior approach.\n\nBut yes, problem seems to have that S consists of 2/25 and 5/22.\n\nBut just to check if there's another rational number. Let me consider some example. Take r=1/55. Then 55*1/55=1/1. The sum of numerator and denominator for r is 1+55=56. For 55r=1/1, sum is 1+1=2. So not equal.\n\nAnother example, r=1/5. These would translate to 55r=11/1, sum for r=1+5=6, sum for 55r=11+1=12. Not equal.\n\nTake 5/5, but that's not reduced. Disregard.\n\nTake r=3/7. Then, 55*3/7=165/7. That is already reduced (since gcd(165,7)=1?), 165 – yes, 7 divides 165? 165 divided by 7 is 23.57~=23. So 165=7×23 +4. So 165 and7 are coprime. Sum: 3+7=10 vs. 165+7=172. Not equal.\n\nWait. How about 2/25: already and 5/22. Any others?\n\nTake r=25/2, but that's not positive— but question says \"positive\", so fractions, same notation. Wait, but 25/2 is same as 2/25 but upside down. But positive, cases are same. Wait, fractions of in lowest terms as a/b where a and b are positive.\n\nBut we have r is positive, so all a and b are positive. So 25/2 is a different r, but would you have 55*25/2=. Wait, 55*25=1375/2.\n\nBut in reduced terms, whether sum equals? But no.\n\nBut, hang on, when I inverted the fractions, suppose 55*(25/2)=1375/2, reduced.\n\nSum for 25/2: 25+2=27. 1375 and 2: g= gcd(1375,2)=1. Then sum is 1375 +2=1377.\n\nNot equal. Hence no.\n\nSo, only the two as found. Hence sum is 169+550=719. So uhm, yeah.\n\n**Final Answer**\n\\boxed{719}"}}},{"rowIdx":5,"cells":{"id":{"kind":"number","value":5,"string":"5"},"source":{"kind":"string","value":"LIMO"},"instruction":{"kind":"string","value":"Let $n=2^{31}3^{19}.$ How many positive integer divisors of $n^2$ are less than $n_{}$ but do not divide $n_{}$ ?"},"response":{"kind":"string","value":"Okay, let's try to figure out this problem. The question is: Let \\( n = 2^{31} \\times 3^{19} \\). How many positive integer divisors of \\( n^2 \\) are less than \\( n \\) but do not divide \\( n \\)?\n\nFirst, I need to understand what's being asked here. We have to find divisors of \\( n^2 \\) that are less than \\( n \\) but aren't divisors of \\( n \\). So, essentially, these are numbers that divide \\( n^2 \\) but aren't factors of \\( n \\) itself and are smaller than \\( n \\).\n\nLet me recall some number theory concepts. If a number \\( n \\) has a prime factorization \\( n = p_1^{a_1} p_2^{a_2} \\dots p_k^{a_k} \\), then the number of divisors of \\( n \\) is \\( (a_1 + 1)(a_2 + 1) \\dots (a_k + 1) \\). Similarly, \\( n^2 \\) would have a prime factorization \\( n^2 = p_1^{2a_1} p_2^{2a_2} \\dots p_k^{2a_k} \\), so its number of divisors would be \\( (2a_1 + 1)(2a_2 + 1) \\dots (2a_k + 1) \\).\n\nGiven that \\( n = 2^{31} \\times 3^{19} \\), then \\( n^2 = 2^{62} \\times 3^{38} \\). So, the number of divisors of \\( n \\) is \\( (31 + 1)(19 + 1) = 32 \\times 20 = 640 \\). The number of divisors of \\( n^2 \\) would be \\( (62 + 1)(38 + 1) = 63 \\times 39 = 2457 \\).\n\nNow, we need to find the number of divisors of \\( n^2 \\) that are less than \\( n \\) but do not divide \\( n \\). Let me think about how to approach this.\n\nI remember that for any number \\( m \\), the divisors come in pairs that multiply to \\( m \\). For \\( n^2 \\), the divisors less than \\( n \\) would pair with divisors greater than \\( n \\) such that their product is \\( n^2 \\). So, the total number of divisors of \\( n^2 \\) less than \\( n \\) should be equal to the number of divisors greater than \\( n \\). Since \\( n^2 \\) is a perfect square, \\( n \\) itself is the square root, so the number of divisors less than \\( n \\) would be \\( \\frac{\\text{number of divisors of } n^2 - 1}{2} \\). Wait, because \\( n \\) is a divisor of \\( n^2 \\), so we subtract 1 (to exclude \\( n \\) itself) and divide by 2. So, that would be \\( \\frac{2457 - 1}{2} = 1228 \\).\n\nBut these 1228 divisors of \\( n^2 \\) that are less than \\( n \\) include divisors that also divide \\( n \\). So, we need to subtract the number of divisors of \\( n \\) that are less than \\( n \\) to get the ones that do not divide \\( n \\).\n\nWait, the number of divisors of \\( n \\) that are less than \\( n \\) is \\( 640 - 1 = 639 \\), since we exclude \\( n \\) itself. Therefore, the number of divisors of \\( n^2 \\) that are less than \\( n \\) but do not divide \\( n \\) would be \\( 1228 - 639 = 589 \\).\n\nBut let me verify this approach step by step to make sure I haven't made a mistake.\n\nFirst, confirm the number of divisors of \\( n \\): \\( (31 + 1)(19 + 1) = 32 \\times 20 = 640 \\). Correct.\n\nNumber of divisors of \\( n^2 \\): \\( (62 + 1)(38 + 1) = 63 \\times 39 = 2457 \\). Correct.\n\nDivisors of \\( n^2 \\) come in pairs multiplying to \\( n^2 \\). So, divisors less than \\( n \\) pair with divisors greater than \\( n \\). Since \\( n^2 \\) is a square, \\( n \\) is the square root, so exactly one divisor is equal to \\( n \\). Therefore, the total number of divisors less than \\( n \\) is equal to the number of divisors greater than \\( n \\), which is \\( (2457 - 1)/2 = 1228 \\). That seems right.\n\nNow, the divisors of \\( n^2 \\) less than \\( n \\) include all the divisors of \\( n \\) (except \\( n \\) itself) and some more divisors that don't divide \\( n \\). So, to find the number of divisors of \\( n^2 \\) less than \\( n \\) but not dividing \\( n \\), subtract the number of divisors of \\( n \\) (excluding \\( n \\)) from the total number of divisors of \\( n^2 \\) less than \\( n \\).\n\nNumber of divisors of \\( n \\) less than \\( n \\): 640 - 1 = 639. So, 1228 - 639 = 589. So, the answer should be 589. Hmm.\n\nBut let me think again. Is every divisor of \\( n \\) a divisor of \\( n^2 \\)? Yes, because if d divides n, then n = d * k, so n^2 = d * k * n, so d divides n^2. So, all divisors of n are indeed divisors of n^2.\n\nTherefore, the logic is: total divisors of n^2 less than n are 1228. Subtract the number of divisors of n that are less than n (which is 639), giving 589 divisors of n^2 less than n that do not divide n.\n\nWait, but let me check with an example to ensure this method works.\n\nTake a smaller number, say n = 2^1 * 3^1 = 6.\n\nThen n^2 = 36 = 2^2 * 3^2. Divisors of n: 1, 2, 3, 6. Number of divisors: 4.\n\nDivisors of n^2: 1, 2, 3, 4, 6, 9, 12, 18, 36. Number of divisors: 9.\n\nDivisors of n^2 less than n=6: 1, 2, 3, 4. So, 4 divisors.\n\nBut divisors of n less than n: 1, 2, 3. So, 3 divisors.\n\nTherefore, the answer should be 4 - 3 = 1. Checking which one: the divisors of 36 less than 6 but not dividing 6 are 4. So, correct.\n\nTherefore, the method works here. So, applying the same reasoning to the original problem should be valid.\n\nTherefore, the answer is 1228 - 639 = 589. So, 589. But wait, let me check the arithmetic again.\n\n2457 - 1 = 2456. 2456 / 2 = 1228. Correct.\n\n640 - 1 = 639. Correct.\n\n1228 - 639: 1228 - 600 = 628; 628 - 39 = 589. Correct.\n\nHence, the answer should be 589. Hmm.\n\nWait, but just to be thorough, let me consider another example.\n\nTake n = 2^2 * 3^1 = 12.\n\nn^2 = 144 = 2^4 * 3^2.\n\nDivisors of n: 1, 2, 3, 4, 6, 12. Number of divisors: 6.\n\nDivisors of n^2: 1, 2, 3, 4, 6, 8, 9, 12, 16, 18, 24, 36, 48, 72, 144. Number of divisors: 15.\n\nNumber of divisors of n^2 less than 12: 1, 2, 3, 4, 6, 8, 9. That's 7 divisors.\n\nNumber of divisors of n less than 12: 5.\n\nTherefore, the answer should be 7 - 5 = 2. Checking which ones: 8 and 9. These are divisors of 144 less than 12 that do not divide 12. Correct.\n\nSo, the formula works here as well: total divisors of n^2 less than n: (15 -1)/2 = 7. Divisors of n less than n: 5. Answer: 7 -5 =2. Correct.\n\nTherefore, the method seems valid.\n\nTherefore, returning to the original problem, the answer should be 589. But let me just cross-verify once more with the exponents.\n\nGiven n = 2^{31} * 3^{19}.\n\nNumber of divisors of n: (31 +1)(19 +1)=32*20=640. Correct.\n\nNumber of divisors of n^2: (62 +1)(38 +1)=63*39=2457. Correct.\n\nDivisors of n^2 less than n: (2457 -1)/2=2456/2=1228. Correct.\n\nDivisors of n less than n: 640 -1=639. Correct.\n\nTherefore, the answer is 1228 - 639=589. So, 589.\n\nBut wait, let me think if there's another way to compute this. Maybe using exponents.\n\nA divisor of n^2 can be written as 2^a * 3^b where 0 31 or b >19. So, the divisors of n^2 that do not divide n are exactly those where a >31 or b >19.\n\nBut we need to count those divisors which are also less than n.\n\nSo, perhaps another approach is to compute the number of divisors of n^2 that are less than n and have either a >31 or b >19.\n\nSo, total divisors of n^2 less than n: 1228.\n\nNumber of these that divide n: 639.\n\nTherefore, 1228 -639=589, which is the same as before.\n\nAlternatively, using inclusion-exclusion: the number of divisors of n^2 less than n with a >31 plus the number with b >19 minus the number with both a>31 and b>19.\n\nBut maybe this approach is more complicated, but let's try.\n\nFirst, compute the number of divisors of n^2 with a >31 and 2^a *3^b 31, so a ranges from 32 to 62. But we also need 2^a *3^b 2^{a -31} *3^{b -19} 31, let me set x = a -31 >=1, and y = b -19. But since 2^{x} *3^{y} =1, y can be negative or non-positive.\n\nWait, perhaps it's better to rewrite the inequality as 2^{a}/2^{31} *3^{b}/3^{19} 31, x =a -31 >=1, and 3^{b -19} =2^x.\n\nBut since 3^{19 -b} must be an integer, and 2^x is also an integer, so we need 3^{19 -b} >=2^x where x >=1 and b =2^x, and then b = log_3(2^x) => 19 -b >=x * log_3(2). Therefore, b 3^{b -19} =32, 31 -a 3^{19 -b} >=2.\n\nWhich implies that 19 -b >=1 (since 3^1=3 >=2). So, 19 -b >=1 =>b =32, the maximum b is 18. Wait, but this seems confusing.\n\nWait, let's take an example. Let a=32. Then, 31 -a= -1. So, 2^{31 -a}=1/2. Therefore, 3^{b -19} =2. So, 19 -b >=1 => b =4. Since 3^1=3 =4. So, 19 -b >=2 =>b 2^{-3}=1/8. So, 3^{19 -b} >=8. 3^1=3 =8. So, 19 -b >=2 =>b =8. 3^2=9 >=8, 3^1=3 =2 =>b =8 requires 19 -b >=2, which is b =16. 3^2=9 =16. So, 19 -b >=3 =>b =32. 3^3=27 =32. So, 19 -b >=4 =>b 31 is equal to the number of divisors of n^2 where a ranges from32 to62 and b ranges from0 to such that 2^a *3^b 31, b 2^{a -31} 31 and a a -31 a d=n. But d=n is a divisor of n, so it is excluded. Therefore, all other divisors should pair up. Therefore, the number of non-divisors of n in n^2 should be even. But 1817 is odd. Contradiction. Therefore, my initial assumption must be wrong. Where is the mistake?\n\nWait, maybe the count of divisors of n is wrong? Wait, no. n=2^{31}3^{19}, so the number of divisors is (31+1)(19+1)=32*20=640. Correct.\n\nn^2=2^{62}3^{38}, number of divisors is(62+1)(38+1)=63*39=2457. Correct.\n\nTherefore, 2457 -640=1817, which is odd. Therefore, there is a contradiction. Therefore, my reasoning must be flawed. Maybe I need to re-examine the pairing argument.\n\nWait, if d is a divisor of n^2 not dividing n, then n^2/d is also a divisor of n^2 not dividing n. So, (d, n^2/d) form pairs. Therefore, the total number of such divisors should be even. Therefore, 1817 must be even. But 1817 divided by2 is908.5, which is not an integer. Hence, contradiction. Therefore, my calculation is wrong.\n\nWait, but 2457 is odd, 640 is even, so2457 -640=1817 is odd. But this contradicts the pairing. Therefore, where is the error?\n\nWait, maybe the problem is that some of the divisors d of n^2 not dividing n satisfy d =n^2/d, but that would imply d =n, which divides n. Therefore, there are no such divisors. Therefore, all divisors must come in pairs, so the total number should be even. Therefore, the calculation must be wrong.\n\nBut 2457 -640=1817, which is odd. Therefore, this suggests that the original problem is wrong? That can't be. Wait, no. Wait, maybe I miscalculated the number of divisors of n^2.\n\nWait, n=2^{31}3^{19}. So, n^2=2^{62}3^{38}. Then number of divisors is(62+1)(38+1)=63*39=2457. 63*39: 60*39=2340, 3*39=117, 2340+117=2457. Correct.\n\nNumber of divisors of n: (31+1)(19+1)=32*20=640. Correct.\n\n640 is even. 2457 is odd. 2457-640=1817 is odd. So, contradiction.\n\nWait, so perhaps my mistake is in assuming that all divisors of n^2 that don't divide n come in pairs. But in reality, if d is a divisor of n^2 not dividing n, then n^2/d is also a divisor of n^2 not dividing n. Therefore, if d ≠n^2/d, they form a pair. If d =n^2/d, then d =n, but d =n divides n, so it's excluded. Therefore, the number of such divisors must be even. Therefore, 1817 must be even. Hence, the result 1817 is impossible. Therefore, there must be a miscalculation.\n\nWait, but 2457-640=1817 is definitely correct. Therefore, the contradiction suggests an error in the problem statement or my understanding.\n\nWait, hold on. Wait, divisors of n^2 include all the divisors of n, right? Because if d divides n, then d divides n^2. Yes. Therefore, the number of divisors of n^2 that are not divisors of n is2457 -640=1817. But since n^2 is a square, the number of divisors less than n is equal to the number of divisors greater than n. Which is(2457 -1)/2=1228. Therefore, the number of divisors less than n is1228, which includes divisors of n (which are639) and others. Therefore, the number of divisors of n^2 less than n that do not divide n is1228 -639=589. And the number of divisors of n^2 greater than n that do not divide n is also589. Then, total divisors of n^2 not dividing n would be589 +589=1178. But 1178 ≠1817. Therefore, discrepancy.\n\nWait, so where is the problem?\n\nWait, total divisors of n^2 not dividing n:1817.\n\nDivisors of n^2 not dividing n and less than n:589.\n\nDivisors of n^2 not dividing n and greater than n:589.\n\nDivisors of n^2 equal to n:1 (but n divides n, so it's excluded).\n\nBut 589 +589=1178≠1817. Therefore, my previous reasoning is flawed.\n\nWait, so the discrepancy is1817 -1178=639. Which is exactly the number of divisors of n (excluding n itself). Wait, no. Wait, 1817 =1178 + 639? 1178 +639=1817. Yes. Therefore, this suggests that there are 639 divisors of n^2 not dividing n that are equal to... what? But n^2 divisors not dividing n can't be equal to divisors of n. Wait, this is confusing.\n\nWait, perhaps my original approach is wrong. Let me clarify.\n\nTotal divisors of n^2:2457.\n\nDivisors of n:640. All of these are also divisors of n^2.\n\nTherefore, the remaining divisors of n^2 are2457 -640=1817, which do not divide n.\n\nThese 1817 divisors come in pairs (d, n^2/d) where d n, or vice versa.\n\nBut the number of such pairs should be equal to the number of divisors less than n which do not divide n, multiplied by2. But since n^2 is a perfect square, only n is the square root, so all other divisors pair up.\n\nBut according to earlier count, divisors of n^2 less than n:1228. This includes divisors of n (639) and those that don't divide n (589). Similarly, divisors greater than n:1228, which includes 639 divisors of n (since each divisor of n greater than1 has a complement divisor less than n) and 589 that don't divide n.\n\nWait, no. Wait, divisors of n greater than n would only be n itself, but n is not greater than n. Wait, divisors of n are from1 to n. So, divisors of n are all less than or equal to n. Therefore, divisors of n^2 greater than n are all the ones not dividing n, except for those that are multiples.\n\nWait, this is getting too confusing. Maybe we need to visualize.\n\nImagine the set of divisors of n^2. They can be partitioned into three categories:\n\n1. Divisors that are also divisors of n and less than n:639.\n\n2. The divisor n itself:1.\n\n3. Divisors that do not divide n:1817.\n\nNow, the divisors that do not divide n can be split into those less than n and those greater than n. Let x be the number of divisors of n^2 that do not divide n and are less than n. Then, since each such divisor pairs with one greater than n, the number of divisors greater than n is also x. Additionally, the divisor n itself is in the middle.\n\nBut the total number of divisors of n^2 is2457=639 +1 +x +x.\n\nTherefore, 2457=640 +2x =>2x=2457 -640=1817 =>x=1817/2=908.5. But x must be an integer. Contradiction.\n\nTherefore, this suggests that there's an error in our assumption that every divisor of n^2 not dividing n pairs with another such divisor. However, since 1817 is odd, this is impossible. Therefore, the mistake must be in the problem statement or my calculations.\n\nWait, but the problem statement is given, so likely my mistake is in the calculations.\n\nWait, let's double-check the number of divisors.\n\nGiven n=2^{31}3^{19}, so n^2=2^{62}3^{38}.\n\nNumber of divisors of n^2: (62 +1)(38 +1)=63*39=2457. Correct.\n\nNumber of divisors of n: (31 +1)(19 +1)=32*20=640. Correct.\n\nSo, 2457 -640=1817. Correct.\n\nThe contradiction arises because 1817 is odd, but according to pairing, it should be even. Therefore, there must be a divisor d of n^2 not dividing n such that d =n^2/d. But d=n^2/d impl | 2026-01-13T09:29:16 |
https://support.atlassian.com/jira-work-management | Jira Work Management Cloud support | Jira Work Management Cloud | Atlassian Support Skip to main content Jira Work Management Support Apps Documentation Resources Contact us Sign in Sign in Atlassian Support Jira Work Management Jira Work Management Cloud support Documentation Get help using and administering apps. View documentation Community Find answers, support, and inspiration from other Atlassian users. Visit Atlassian Community System Status Check the health of our cloud apps and services View system status Suggestions and bug reports Find existing feature suggestions and bug reports. View suggestions and bugs Marketplace apps Find features to customize your apps View Marketplace Billing and licensing See FAQs about billing and licensing. View FAQs What's new See the latest and greatest updates and new features for your Atlassian cloud apps and services. View release notes Not finding the help you need? Accessibility Notice at Collection Privacy Policy Terms of Use Security 2026 Atlassian | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?modality=modality:text&p=0&sort=trending | Text Datasets – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":401131,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities Reset Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 401,131 Full-text search Edit filters Sort: Trending Active filters: text Clear all HuggingFaceFW/finetranslations Viewer • Updated 4 days ago • 3.33B • 7.34k • 143 xiuhuywh/DRIM-VisualReasonHard Viewer • Updated 4 days ago • 17.1k • 1.8k • 96 WNT3D/Ultimate-Offensive-Red-Team Viewer • Updated Aug 23, 2025 • 25.6k • 481 • 120 xiuhuywh/DRIM-ColdstartSFT Viewer • Updated 4 days ago • 44.3k • 4.93k • 84 miromind-ai/MiroVerse-v0.1 Viewer • Updated Nov 19, 2025 • 228k • 767 • 177 123olp/binance-futures-ohlcv-2018-2026 Viewer • Updated 2 days ago • 425M • 478 • 96 DatologyAI/DatBench Viewer • Updated 2 days ago • 43.5k • 286 • 68 MiniMaxAI/OctoCodingBench Viewer • Updated about 5 hours ago • 72 • 68 Salesforce/wikitext Viewer • Updated Jan 4, 2024 • 3.71M • 793k • 616 ScienceOne-AI/S1-MMAlign Viewer • Updated 8 days ago • 21.1M • 7.54k • 70 TeichAI/glm-4.7-2000x Viewer • Updated 21 days ago • 1.98k • 339 • 71 facebook/research-plan-gen Viewer • Updated 11 days ago • 22.5k • 3.61k • 272 OpenDataArena/ODA-Mixture-500k Viewer • Updated about 22 hours ago • 506k • 5.49k • 116 nvidia/embed-nemotron-dataset-v1 Viewer • Updated 1 day ago • 12.8M • 204 • 50 DatologyAI/DatBench-Full Viewer • Updated 7 days ago • 195k • 231 • 46 OpenDataArena/ODA-Math-460k Viewer • Updated 13 days ago • 460k • 4.93k • 96 tatsu-lab/alpaca Viewer • Updated May 22, 2023 • 52k • 44.6k • 889 missvector/linux-commands Viewer • Updated about 16 hours ago • 71.8k • 617 • 84 OpenDataArena/ODA-Mixture-100k Viewer • Updated 13 days ago • 101k • 3.56k • 90 Anthropic/hh-rlhf Viewer • Updated May 26, 2023 • 169k • 22.7k • 1.63k Rapidata/bananamark-dataset Viewer • Updated Dec 12, 2025 • 2.16k • 62 • 28 wikimedia/wikipedia Viewer • Updated Jan 9, 2024 • 61.6M • 74.6k • 1.12k TeichAI/claude-4.5-opus-high-reasoning-250x Viewer • Updated Nov 28, 2025 • 250 • 8.33k • 161 openmed-community/MedReason-Stenographic Viewer • Updated 4 days ago • 31.5k • 34 • 22 m-a-p/COIG-CQIA Viewer • Updated Apr 18, 2024 • 44.7k • 5.12k • 691 HuggingFaceFW/finepdfs Viewer • Updated 4 days ago • 476M • 23.2k • 711 Bingguang/HardGen Viewer • Updated 5 days ago • 17k • 281 • 65 MiniMaxAI/VIBE Viewer • Updated 21 days ago • 200 • 10.5k • 249 MLCommons/peoples_speech Viewer • Updated Nov 20, 2024 • 8.05M • 13.6k • 246 LEMAS-Project/LEMAS-Dataset-train Viewer • Updated 4 days ago • 125M • 3.62k • 15 Previous 1 2 3 ... 100 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://www.linkedin.com/signup/cold-join?session_redirect=%2Fservices%2Fproducts%2Ftencentglobal-tencent-cloud-instant-messaging-im%2F&trk=products_details_guest_nav-header-join | Sign Up | LinkedIn Make the most of your professional life Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Keep me logged in First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=05e1YdwAAAAJ&hl=ko&oe=ASCII | Jianhai Chen - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 1482 917 h-index 20 18 i10-index 29 25 0 240 120 60 180 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 15 24 38 43 52 64 62 58 82 107 109 149 194 232 229 4 공개 액세스 모두 보기 모두 보기 자료 20개 자료 4개 공개 비공개 재정 지원 요구사항 기준 팔로우 Jianhai Chen Zhejiang University zju.edu.cn의 이메일 확인됨 Computer science 학술자료 인용 공개 액세스 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Live migration of multiple virtual machines with resource reservation in cloud computing environments K Ye, X Jiang, D Huang, J Chen, B Wang 2011 IEEE 4th International Conference on Cloud Computing, 267-274 , 2011 253 2011 Behavior pattern clustering in blockchain networks B Huang, Z Liu, J Chen, A Liu, Q Liu, Q He Multimedia Tools and Applications 76 (19), 20099-20110 , 2017 124 2017 Fedrecattack: Model poisoning attack to federated recommendation D Rong, S Ye, R Zhao, HN Yuen, J Chen, Q He 2022 IEEE 38th International Conference on Data Engineering (ICDE), 2643-2655 , 2022 108 2022 Adversarial captchas C Shi, X Xu, S Ji, K Bu, J Chen, R Beyah, T Wang IEEE transactions on cybernetics 52 (7), 6095-6108 , 2021 73 2021 V-fuzz: Vulnerability prediction-assisted evolutionary fuzzing for binary programs Y Li, S Ji, C Lyu, Y Chen, J Chen, Q Gu, C Wu, R Beyah IEEE transactions on cybernetics 52 (5), 3745-3756 , 2020 70 2020 Smartseed: Smart seed generation for efficient fuzzing C Lyu, S Ji, Y Li, J Zhou, J Chen, J Chen arXiv preprint arXiv:1807.02606 , 2018 70 2018 Non-cooperative games on multidimensional resource allocation D Ye, J Chen Future Generation Computer Systems 29 (6), 1345-1352 , 2013 70 2013 V-fuzz: Vulnerability-oriented evolutionary fuzzing Y Li, S Ji, C Lv, Y Chen, J Chen, Q Gu, C Wu arXiv preprint arXiv:1901.01142 , 2019 66 2019 Poisoning deep learning based recommender model in federated learning scenarios D Rong, Q He, J Chen arXiv preprint arXiv:2204.13594 , 2022 65 2022 Towards understanding the security of modern image captchas and underground captcha-solving services H Weng, B Zhao, S Ji, J Chen, T Wang, Q He, R Beyah Big Data Mining and Analytics 2 (2), 118-144 , 2019 55 2019 Virt-LM: a benchmark for live migration of virtual machine D Huang, D Ye, Q He, J Chen, K Ye Proceedings of the 2nd ACM/SPEC International Conference on Performance�… , 2011 50 2011 AAGA: Affinity-aware grouping for allocation of virtual machines J Chen, K Chiew, D Ye, L Zhu, W Chen 2013 IEEE 27th International Conference on Advanced Information Networking�… , 2013 47 2013 Towards evaluating the security of real-world deployed image captchas B Zhao, H Weng, S Ji, J Chen, T Wang, Q He, R Beyah Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security�… , 2018 42 2018 De-sag: On the de-anonymization of structure-attribute graph data S Ji, T Wang, J Chen, W Li, P Mittal, R Beyah IEEE Transactions on Dependable and Secure Computing 16 (4), 594-607 , 2017 37 2017 Rapido: Scaling blockchain with multi-path payment channels C Lin, N Ma, X Wang, J Chen Neurocomputing 406, 322-332 , 2020 29 2020 Cats: cross-platform e-commerce fraud detection H Weng, S Ji, F Duan, Z Li, J Chen, Q He, T Wang 2019 ieee 35th international conference on data engineering (icde), 1874-1885 , 2019 29 2019 Informed live migration strategies of virtual machines for cluster load balancing X Li, Q He, J Chen, K Ye, T Yin IFIP International Conference on Network and Parallel Computing, 111-122 , 2011 26 2011 Detecting missed security operations through differential checking of object-based similar paths D Liu, Q Wu, S Ji, K Lu, Z Liu, J Chen, Q He Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications�… , 2021 24 2021 Mufuzz: Sequence-aware mutation and seed mask guidance for blockchain smart contract fuzzing P Qian, H Wu, Z Du, T Vural, D Rong, Z Cao, L Zhang, Y Wang, J Chen, ... 2024 IEEE 40th International Conference on Data Engineering (ICDE), 1972-1985 , 2024 20 2024 Demystifying bitcoin address behavior via graph neural networks Z Huang, Y Huang, P Qian, J Chen, Q He 2023 IEEE 39th International Conference on Data Engineering (ICDE), 1747-1760 , 2023 20 2023 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://doc.rust-lang.org/book/print.html#who-rust-is-for | The Rust Programming Language Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu The Rust Programming Language The Rust Programming Language by Steve Klabnik, Carol Nichols, and Chris Krycho, with contributions from the Rust Community This version of the text assumes you’re using Rust 1.85.0 (released 2025-02-17) or later with edition = "2024" in the Cargo.toml file of all projects to configure them to use Rust 2024 Edition idioms. See the “Installation” section of Chapter 1 for instructions on installing or updating Rust, and see Appendix E for information on editions. The HTML format is available online at https://doc.rust-lang.org/stable/book/ and offline with installations of Rust made with rustup ; run rustup doc --book to open. Several community translations are also available. This text is available in paperback and ebook format from No Starch Press . 🚨 Want a more interactive learning experience? Try out a different version of the Rust Book, featuring: quizzes, highlighting, visualizations, and more : https://rust-book.cs.brown.edu Foreword The Rust programming language has come a long way in a few short years, from its creation and incubation by a small and nascent community of enthusiasts, to becoming one of the most loved and in-demand programming languages in the world. Looking back, it was inevitable that the power and promise of Rust would turn heads and gain a foothold in systems programming. What was not inevitable was the global growth in interest and innovation that permeated through open source communities and catalyzed wide-scale adoption across industries. At this point in time, it is easy to point to the wonderful features that Rust has to offer to explain this explosion in interest and adoption. Who doesn’t want memory safety, and fast performance, and a friendly compiler, and great tooling, among a host of other wonderful features? The Rust language you see today combines years of research in systems programming with the practical wisdom of a vibrant and passionate community. This language was designed with purpose and crafted with care, offering developers a tool that makes it easier to write safe, fast, and reliable code. But what makes Rust truly special is its roots in empowering you, the user, to achieve your goals. This is a language that wants you to succeed, and the principle of empowerment runs through the core of the community that builds, maintains, and advocates for this language. Since the previous edition of this definitive text, Rust has further developed into a truly global and trusted language. The Rust Project is now robustly supported by the Rust Foundation, which also invests in key initiatives to ensure that Rust is secure, stable, and sustainable. This edition of The Rust Programming Language is a comprehensive update, reflecting the language’s evolution over the years and providing valuable new information. But it is not just a guide to syntax and libraries—it’s an invitation to join a community that values quality, performance, and thoughtful design. Whether you’re a seasoned developer looking to explore Rust for the first time or an experienced Rustacean looking to refine your skills, this edition offers something for everyone. The Rust journey has been one of collaboration, learning, and iteration. The growth of the language and its ecosystem is a direct reflection of the vibrant, diverse community behind it. The contributions of thousands of developers, from core language designers to casual contributors, are what make Rust such a unique and powerful tool. By picking up this book, you’re not just learning a new programming language—you’re joining a movement to make software better, safer, and more enjoyable to work with. Welcome to the Rust community! Bec Rumbul, Executive Director of the Rust Foundation Introduction Note: This edition of the book is the same as The Rust Programming Language available in print and ebook format from No Starch Press . Welcome to The Rust Programming Language , an introductory book about Rust. The Rust programming language helps you write faster, more reliable software. High-level ergonomics and low-level control are often at odds in programming language design; Rust challenges that conflict. Through balancing powerful technical capacity and a great developer experience, Rust gives you the option to control low-level details (such as memory usage) without all the hassle traditionally associated with such control. Who Rust Is For Rust is ideal for many people for a variety of reasons. Let’s look at a few of the most important groups. Teams of Developers Rust is proving to be a productive tool for collaborating among large teams of developers with varying levels of systems programming knowledge. Low-level code is prone to various subtle bugs, which in most other languages can only be caught through extensive testing and careful code review by experienced developers. In Rust, the compiler plays a gatekeeper role by refusing to compile code with these elusive bugs, including concurrency bugs. By working alongside the compiler, the team can spend its time focusing on the program’s logic rather than chasing down bugs. Rust also brings contemporary developer tools to the systems programming world: Cargo, the included dependency manager and build tool, makes adding, compiling, and managing dependencies painless and consistent across the Rust ecosystem. The rustfmt formatting tool ensures a consistent coding style across developers. The Rust Language Server powers integrated development environment (IDE) integration for code completion and inline error messages. By using these and other tools in the Rust ecosystem, developers can be productive while writing systems-level code. Students Rust is for students and those who are interested in learning about systems concepts. Using Rust, many people have learned about topics like operating systems development. The community is very welcoming and happy to answer students’ questions. Through efforts such as this book, the Rust teams want to make systems concepts more accessible to more people, especially those new to programming. Companies Hundreds of companies, large and small, use Rust in production for a variety of tasks, including command line tools, web services, DevOps tooling, embedded devices, audio and video analysis and transcoding, cryptocurrencies, bioinformatics, search engines, Internet of Things applications, machine learning, and even major parts of the Firefox web browser. Open Source Developers Rust is for people who want to build the Rust programming language, community, developer tools, and libraries. We’d love to have you contribute to the Rust language. People Who Value Speed and Stability Rust is for people who crave speed and stability in a language. By speed, we mean both how quickly Rust code can run and the speed at which Rust lets you write programs. The Rust compiler’s checks ensure stability through feature additions and refactoring. This is in contrast to the brittle legacy code in languages without these checks, which developers are often afraid to modify. By striving for zero-cost abstractions—higher-level features that compile to lower-level code as fast as code written manually—Rust endeavors to make safe code be fast code as well. The Rust language hopes to support many other users as well; those mentioned here are merely some of the biggest stakeholders. Overall, Rust’s greatest ambition is to eliminate the trade-offs that programmers have accepted for decades by providing safety and productivity, speed and ergonomics. Give Rust a try, and see if its choices work for you. Who This Book Is For This book assumes that you’ve written code in another programming language, but it doesn’t make any assumptions about which one. We’ve tried to make the material broadly accessible to those from a wide variety of programming backgrounds. We don’t spend a lot of time talking about what programming is or how to think about it. If you’re entirely new to programming, you would be better served by reading a book that specifically provides an introduction to programming. How to Use This Book In general, this book assumes that you’re reading it in sequence from front to back. Later chapters build on concepts in earlier chapters, and earlier chapters might not delve into details on a particular topic but will revisit the topic in a later chapter. You’ll find two kinds of chapters in this book: concept chapters and project chapters. In concept chapters, you’ll learn about an aspect of Rust. In project chapters, we’ll build small programs together, applying what you’ve learned so far. Chapter 2, Chapter 12, and Chapter 21 are project chapters; the rest are concept chapters. Chapter 1 explains how to install Rust, how to write a “Hello, world!” program, and how to use Cargo, Rust’s package manager and build tool. Chapter 2 is a hands-on introduction to writing a program in Rust, having you build up a number-guessing game. Here, we cover concepts at a high level, and later chapters will provide additional detail. If you want to get your hands dirty right away, Chapter 2 is the place for that. If you’re a particularly meticulous learner who prefers to learn every detail before moving on to the next, you might want to skip Chapter 2 and go straight to Chapter 3 , which covers Rust features that are similar to those of other programming languages; then, you can return to Chapter 2 when you’d like to work on a project applying the details you’ve learned. In Chapter 4 , you’ll learn about Rust’s ownership system. Chapter 5 discusses structs and methods. Chapter 6 covers enums, match expressions, and the if let and let...else control flow constructs. You’ll use structs and enums to make custom types. In Chapter 7 , you’ll learn about Rust’s module system and about privacy rules for organizing your code and its public application programming interface (API). Chapter 8 discusses some common collection data structures that the standard library provides: vectors, strings, and hash maps. Chapter 9 explores Rust’s error-handling philosophy and techniques. Chapter 10 digs into generics, traits, and lifetimes, which give you the power to define code that applies to multiple types. Chapter 11 is all about testing, which even with Rust’s safety guarantees is necessary to ensure that your program’s logic is correct. In Chapter 12 , we’ll build our own implementation of a subset of functionality from the grep command line tool that searches for text within files. For this, we’ll use many of the concepts we discussed in the previous chapters. Chapter 13 explores closures and iterators: features of Rust that come from functional programming languages. In Chapter 14 , we’ll examine Cargo in more depth and talk about best practices for sharing your libraries with others. Chapter 15 discusses smart pointers that the standard library provides and the traits that enable their functionality. In Chapter 16 , we’ll walk through different models of concurrent programming and talk about how Rust helps you program in multiple threads fearlessly. In Chapter 17 , we build on that by exploring Rust’s async and await syntax, along with tasks, futures, and streams, and the lightweight concurrency model they enable. Chapter 18 looks at how Rust idioms compare to object-oriented programming principles you might be familiar with. Chapter 19 is a reference on patterns and pattern matching, which are powerful ways of expressing ideas throughout Rust programs. Chapter 20 contains a smorgasbord of advanced topics of interest, including unsafe Rust, macros, and more about lifetimes, traits, types, functions, and closures. In Chapter 21 , we’ll complete a project in which we’ll implement a low-level multithreaded web server! Finally, some appendixes contain useful information about the language in a more reference-like format. Appendix A covers Rust’s keywords, Appendix B covers Rust’s operators and symbols, Appendix C covers derivable traits provided by the standard library, Appendix D covers some useful development tools, and Appendix E explains Rust editions. In Appendix F , you can find translations of the book, and in Appendix G we’ll cover how Rust is made and what nightly Rust is. There is no wrong way to read this book: If you want to skip ahead, go for it! You might have to jump back to earlier chapters if you experience any confusion. But do whatever works for you. An important part of the process of learning Rust is learning how to read the error messages the compiler displays: These will guide you toward working code. As such, we’ll provide many examples that don’t compile along with the error message the compiler will show you in each situation. Know that if you enter and run a random example, it may not compile! Make sure you read the surrounding text to see whether the example you’re trying to run is meant to error. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Ferris will also help you distinguish code that isn’t meant to work: Ferris Meaning This code does not compile! This code panics! This code does not produce the desired behavior. In most situations, we’ll lead you to the correct version of any code that doesn’t compile. Source Code The source files from which this book is generated can be found on GitHub . Getting Started Let’s start your Rust journey! There’s a lot to learn, but every journey starts somewhere. In this chapter, we’ll discuss: Installing Rust on Linux, macOS, and Windows Writing a program that prints Hello, world! Using cargo , Rust’s package manager and build system Installation The first step is to install Rust. We’ll download Rust through rustup , a command line tool for managing Rust versions and associated tools. You’ll need an internet connection for the download. Note: If you prefer not to use rustup for some reason, please see the Other Rust Installation Methods page for more options. The following steps install the latest stable version of the Rust compiler. Rust’s stability guarantees ensure that all the examples in the book that compile will continue to compile with newer Rust versions. The output might differ slightly between versions because Rust often improves error messages and warnings. In other words, any newer, stable version of Rust you install using these steps should work as expected with the content of this book. Command Line Notation In this chapter and throughout the book, we’ll show some commands used in the terminal. Lines that you should enter in a terminal all start with $ . You don’t need to type the $ character; it’s the command line prompt shown to indicate the start of each command. Lines that don’t start with $ typically show the output of the previous command. Additionally, PowerShell-specific examples will use > rather than $ . Installing rustup on Linux or macOS If you’re using Linux or macOS, open a terminal and enter the following command: $ curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh The command downloads a script and starts the installation of the rustup tool, which installs the latest stable version of Rust. You might be prompted for your password. If the install is successful, the following line will appear: Rust is installed now. Great! You will also need a linker , which is a program that Rust uses to join its compiled outputs into one file. It is likely you already have one. If you get linker errors, you should install a C compiler, which will typically include a linker. A C compiler is also useful because some common Rust packages depend on C code and will need a C compiler. On macOS, you can get a C compiler by running: $ xcode-select --install Linux users should generally install GCC or Clang, according to their distribution’s documentation. For example, if you use Ubuntu, you can install the build-essential package. Installing rustup on Windows On Windows, go to https://www.rust-lang.org/tools/install and follow the instructions for installing Rust. At some point in the installation, you’ll be prompted to install Visual Studio. This provides a linker and the native libraries needed to compile programs. If you need more help with this step, see https://rust-lang.github.io/rustup/installation/windows-msvc.html . The rest of this book uses commands that work in both cmd.exe and PowerShell. If there are specific differences, we’ll explain which to use. Troubleshooting To check whether you have Rust installed correctly, open a shell and enter this line: $ rustc --version You should see the version number, commit hash, and commit date for the latest stable version that has been released, in the following format: rustc x.y.z (abcabcabc yyyy-mm-dd) If you see this information, you have installed Rust successfully! If you don’t see this information, check that Rust is in your %PATH% system variable as follows. In Windows CMD, use: > echo %PATH% In PowerShell, use: > echo $env:Path In Linux and macOS, use: $ echo $PATH If that’s all correct and Rust still isn’t working, there are a number of places you can get help. Find out how to get in touch with other Rustaceans (a silly nickname we call ourselves) on the community page . Updating and Uninstalling Once Rust is installed via rustup , updating to a newly released version is easy. From your shell, run the following update script: $ rustup update To uninstall Rust and rustup , run the following uninstall script from your shell: $ rustup self uninstall Reading the Local Documentation The installation of Rust also includes a local copy of the documentation so that you can read it offline. Run rustup doc to open the local documentation in your browser. Any time a type or function is provided by the standard library and you’re not sure what it does or how to use it, use the application programming interface (API) documentation to find out! Using Text Editors and IDEs This book makes no assumptions about what tools you use to author Rust code. Just about any text editor will get the job done! However, many text editors and integrated development environments (IDEs) have built-in support for Rust. You can always find a fairly current list of many editors and IDEs on the tools page on the Rust website. Working Offline with This Book In several examples, we will use Rust packages beyond the standard library. To work through those examples, you will either need to have an internet connection or to have downloaded those dependencies ahead of time. To download the dependencies ahead of time, you can run the following commands. (We’ll explain what cargo is and what each of these commands does in detail later.) $ cargo new get-dependencies $ cd get-dependencies $ cargo add rand@0.8.5 trpl@0.2.0 This will cache the downloads for these packages so you will not need to download them later. Once you have run this command, you do not need to keep the get-dependencies folder. If you have run this command, you can use the --offline flag with all cargo commands in the rest of the book to use these cached versions instead of attempting to use the network. Hello, World! Now that you’ve installed Rust, it’s time to write your first Rust program. It’s traditional when learning a new language to write a little program that prints the text Hello, world! to the screen, so we’ll do the same here! Note: This book assumes basic familiarity with the command line. Rust makes no specific demands about your editing or tooling or where your code lives, so if you prefer to use an IDE instead of the command line, feel free to use your favorite IDE. Many IDEs now have some degree of Rust support; check the IDE’s documentation for details. The Rust team has been focusing on enabling great IDE support via rust-analyzer . See Appendix D for more details. Project Directory Setup You’ll start by making a directory to store your Rust code. It doesn’t matter to Rust where your code lives, but for the exercises and projects in this book, we suggest making a projects directory in your home directory and keeping all your projects there. Open a terminal and enter the following commands to make a projects directory and a directory for the “Hello, world!” project within the projects directory. For Linux, macOS, and PowerShell on Windows, enter this: $ mkdir ~/projects $ cd ~/projects $ mkdir hello_world $ cd hello_world For Windows CMD, enter this: > mkdir "%USERPROFILE%\projects" > cd /d "%USERPROFILE%\projects" > mkdir hello_world > cd hello_world Rust Program Basics Next, make a new source file and call it main.rs . Rust files always end with the .rs extension. If you’re using more than one word in your filename, the convention is to use an underscore to separate them. For example, use hello_world.rs rather than helloworld.rs . Now open the main.rs file you just created and enter the code in Listing 1-1. Filename: main.rs fn main() { println!("Hello, world!"); } Listing 1-1 : A program that prints Hello, world! Save the file and go back to your terminal window in the ~/projects/hello_world directory. On Linux or macOS, enter the following commands to compile and run the file: $ rustc main.rs $ ./main Hello, world! On Windows, enter the command .\main instead of ./main : > rustc main.rs > .\main Hello, world! Regardless of your operating system, the string Hello, world! should print to the terminal. If you don’t see this output, refer back to the “Troubleshooting” part of the Installation section for ways to get help. If Hello, world! did print, congratulations! You’ve officially written a Rust program. That makes you a Rust programmer—welcome! The Anatomy of a Rust Program Let’s review this “Hello, world!” program in detail. Here’s the first piece of the puzzle: fn main() { } These lines define a function named main . The main function is special: It is always the first code that runs in every executable Rust program. Here, the first line declares a function named main that has no parameters and returns nothing. If there were parameters, they would go inside the parentheses ( () ). The function body is wrapped in {} . Rust requires curly brackets around all function bodies. It’s good style to place the opening curly bracket on the same line as the function declaration, adding one space in between. Note: If you want to stick to a standard style across Rust projects, you can use an automatic formatter tool called rustfmt to format your code in a particular style (more on rustfmt in Appendix D ). The Rust team has included this tool with the standard Rust distribution, as rustc is, so it should already be installed on your computer! The body of the main function holds the following code: #![allow(unused)] fn main() { println!("Hello, world!"); } This line does all the work in this little program: It prints text to the screen. There are three important details to notice here. First, println! calls a Rust macro. If it had called a function instead, it would be entered as println (without the ! ). Rust macros are a way to write code that generates code to extend Rust syntax, and we’ll discuss them in more detail in Chapter 20 . For now, you just need to know that using a ! means that you’re calling a macro instead of a normal function and that macros don’t always follow the same rules as functions. Second, you see the "Hello, world!" string. We pass this string as an argument to println! , and the string is printed to the screen. Third, we end the line with a semicolon ( ; ), which indicates that this expression is over, and the next one is ready to begin. Most lines of Rust code end with a semicolon. Compilation and Execution You’ve just run a newly created program, so let’s examine each step in the process. Before running a Rust program, you must compile it using the Rust compiler by entering the rustc command and passing it the name of your source file, like this: $ rustc main.rs If you have a C or C++ background, you’ll notice that this is similar to gcc or clang . After compiling successfully, Rust outputs a binary executable. On Linux, macOS, and PowerShell on Windows, you can see the executable by entering the ls command in your shell: $ ls main main.rs On Linux and macOS, you’ll see two files. With PowerShell on Windows, you’ll see the same three files that you would see using CMD. With CMD on Windows, you would enter the following: > dir /B %= the /B option says to only show the file names =% main.exe main.pdb main.rs This shows the source code file with the .rs extension, the executable file ( main.exe on Windows, but main on all other platforms), and, when using Windows, a file containing debugging information with the .pdb extension. From here, you run the main or main.exe file, like this: $ ./main # or .\main on Windows If your main.rs is your “Hello, world!” program, this line prints Hello, world! to your terminal. If you’re more familiar with a dynamic language, such as Ruby, Python, or JavaScript, you might not be used to compiling and running a program as separate steps. Rust is an ahead-of-time compiled language, meaning you can compile a program and give the executable to someone else, and they can run it even without having Rust installed. If you give someone a .rb , .py , or .js file, they need to have a Ruby, Python, or JavaScript implementation installed (respectively). But in those languages, you only need one command to compile and run your program. Everything is a trade-off in language design. Just compiling with rustc is fine for simple programs, but as your project grows, you’ll want to manage all the options and make it easy to share your code. Next, we’ll introduce you to the Cargo tool, which will help you write real-world Rust programs. Hello, Cargo! Cargo is Rust’s build system and package manager. Most Rustaceans use this tool to manage their Rust projects because Cargo handles a lot of tasks for you, such as building your code, downloading the libraries your code depends on, and building those libraries. (We call the libraries that your code needs dependencies .) The simplest Rust programs, like the one we’ve written so far, don’t have any dependencies. If we had built the “Hello, world!” project with Cargo, it would only use the part of Cargo that handles building your code. As you write more complex Rust programs, you’ll add dependencies, and if you start a project using Cargo, adding dependencies will be much easier to do. Because the vast majority of Rust projects use Cargo, the rest of this book assumes that you’re using Cargo too. Cargo comes installed with Rust if you used the official installers discussed in the “Installation” section. If you installed Rust through some other means, check whether Cargo is installed by entering the following in your terminal: $ cargo --version If you see a version number, you have it! If you see an error, such as command not found , look at the documentation for your method of installation to determine how to install Cargo separately. Creating a Project with Cargo Let’s create a new project using Cargo and look at how it differs from our original “Hello, world!” project. Navigate back to your projects directory (or wherever you decided to store your code). Then, on any operating system, run the following: $ cargo new hello_cargo $ cd hello_cargo The first command creates a new directory and project called hello_cargo . We’ve named our project hello_cargo , and Cargo creates its files in a directory of the same name. Go into the hello_cargo directory and list the files. You’ll see that Cargo has generated two files and one directory for us: a Cargo.toml file and a src directory with a main.rs file inside. It has also initialized a new Git repository along with a .gitignore file. Git files won’t be generated if you run cargo new within an existing Git repository; you can override this behavior by using cargo new --vcs=git . Note: Git is a common version control system. You can change cargo new to use a different version control system or no version control system by using the --vcs flag. Run cargo new --help to see the available options. Open Cargo.toml in your text editor of choice. It should look similar to the code in Listing 1-2. Filename: Cargo.toml [package] name = "hello_cargo" version = "0.1.0" edition = "2024" [dependencies] Listing 1-2 : Contents of Cargo.toml generated by cargo new This file is in the TOML ( Tom’s Obvious, Minimal Language ) format, which is Cargo’s configuration format. The first line, [package] , is a section heading that indicates that the following statements are configuring a package. As we add more information to this file, we’ll add other sections. The next three lines set the configuration information Cargo needs to compile your program: the name, the version, and the edition of Rust to use. We’ll talk about the edition key in Appendix E . The last line, [dependencies] , is the start of a section for you to list any of your project’s dependencies. In Rust, packages of code are referred to as crates . We won’t need any other crates for this project, but we will in the first project in Chapter 2, so we’ll use this dependencies section then. Now open src/main.rs and take a look: Filename: src/main.rs fn main() { println!("Hello, world!"); } Cargo has generated a “Hello, world!” program for you, just like the one we wrote in Listing 1-1! So far, the differences between our project and the project Cargo generated are that Cargo placed the code in the src directory, and we have a Cargo.toml configuration file in the top directory. Cargo expects your source files to live inside the src directory. The top-level project directory is just for README files, license information, configuration files, and anything else not related to your code. Using Cargo helps you organize your projects. There’s a place for everything, and everything is in its place. If you started a project that doesn’t use Cargo, as we did with the “Hello, world!” project, you can convert it to a project that does use Cargo. Move the project code into the src directory and create an appropriate Cargo.toml file. One easy way to get that Cargo.toml file is to run cargo init , which will create it for you automatically. Building and Running a Cargo Project Now let’s look at what’s different when we build and run the “Hello, world!” program with Cargo! From your hello_cargo directory, build your project by entering the following command: $ cargo build Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 2.85 secs This command creates an executable file in target/debug/hello_cargo (or target\debug\hello_cargo.exe on Windows) rather than in your current directory. Because the default build is a debug build, Cargo puts the binary in a directory named debug . You can run the executable with this command: $ ./target/debug/hello_cargo # or .\target\debug\hello_cargo.exe on Windows Hello, world! If all goes well, Hello, world! should print to the terminal. Running cargo build for the first time also causes Cargo to create a new file at the top level: Cargo.lock . This file keeps track of the exact versions of dependencies in your project. This project doesn’t have dependencies, so the file is a bit sparse. You won’t ever need to change this file manually; Cargo manages its contents for you. We just built a project with cargo build and ran it with ./target/debug/hello_cargo , but we can also use cargo run to compile the code and then run the resultant executable all in one command: $ cargo run Finished dev [unoptimized + debuginfo] target(s) in 0.0 secs Running `target/debug/hello_cargo` Hello, world! Using cargo run is more convenient than having to remember to run cargo build and then use the whole path to the binary, so most developers use cargo run . Notice that this time we didn’t see output indicating that Cargo was compiling hello_cargo . Cargo figured out that the files hadn’t changed, so it didn’t rebuild but just ran the binary. If you had modified your source code, Cargo would have rebuilt the project before running it, and you would have seen this output: $ cargo run Compiling hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.33 secs Running `target/debug/hello_cargo` Hello, world! Cargo also provides a command called cargo check . This command quickly checks your code to make sure it compiles but doesn’t produce an executable: $ cargo check Checking hello_cargo v0.1.0 (file:///projects/hello_cargo) Finished dev [unoptimized + debuginfo] target(s) in 0.32 secs Why would you not want an executable? Often, cargo check is much faster than cargo build because it skips the step of producing an executable. If you’re continually checking your work while writing the code, using cargo check will speed up the process of letting you know if your project is still compiling! As such, many Rustaceans run cargo check periodically as they write their program to make sure it compiles. Then, they run cargo build when they’re ready to use the executable. Let’s recap what we’ve learned so far about Cargo: We can create a project using cargo new . We can build a project using cargo build . We can build and run a project in one step using cargo run . We can build a project without producing a binary to check for errors using cargo check . Instead of saving the result of the build in the same directory as our code, Cargo stores it in the target/debug directory. An additional advantage of using Cargo is that the commands are the same no matter which operating system you’re working on. So, at this point, we’ll no longer provide specific instructions for Linux and macOS versus Windows. Building for Release When your project is finally ready for release, you can use cargo build --release to compile it with optimizations. This command will create an executable in target/release instead of target/debug . The optimizations make your Rust code run faster, but turning them on lengthens the time it takes for your program to compile. This is why there are two different profiles: one for development, when you want to rebuild quickly and often, and another for building the final program you’ll give to a user that won’t be rebuilt repeatedly and that will run as fast as possible. If you’re benchmarking your code’s running time, be sure to run cargo build --release and benchmark with the executable in target/release . Leveraging Cargo’s Conventions With simple projects, Cargo doesn’t provide a lot of value over just using rustc , but it will prove its worth as your programs become more intricate. Once programs grow to multiple files or need a dependency, it’s much easier to let Cargo coordinate the build. Even though the hello_cargo project is simple, it now uses much of the real tooling you’ll use in the rest of your Rust career. In fact, to work on any existing projects, you can use the following commands to check out the code using Git, change to that project’s directory, and build: $ git clone example.org/someproject $ cd someproject $ cargo build For more information about Cargo, check out its documentation . Summary You’re already off to a great start on your Rust journey! In this chapter, you learned how to: Install the latest stable version of Rust using rustup . Update to a newer Rust version. Open locally installed documentation. Write and run a “Hello, world!” program using rustc directly. Create and run a new project using the conventions of Cargo. This is a great time to build a more substantial program to get used to reading and writing Rust code. So, in Chapter 2, we’ll build a guessing game program. If you would rather start by learning how common programming concepts work in Rust, see Chapter 3 and then return to Chapter 2. Programming a Guessing Game Let’s jump into Rust by working through a hands-on project together! This chapter introduces you to a few common Rust concepts by showing you how to use them in a real program. You’ll learn about let , match , methods, associated functions, external crates, and more! In the following chapters, we’ll explore these ideas in more detail. In this chapter, you’ll just practice the fundamentals. We’ll implement a classic beginner programming problem: a guessing game. Here’s how it works: The program will generate a random integer between 1 and 100. It will then prompt the player to enter a guess. After a guess is entered, the program will indicate whether the guess is too low or too high. If the guess is correct, the game will print a congratulatory message and exit. Setting Up a New Project To set up a new project, go to the projects directory that you created in Chapter 1 and make a new project using Cargo, like so: $ cargo new guessing_game $ cd guessing_game The first command, cargo new , takes the name of the project ( guessing_game ) as the first argument. The second command changes to the new project’s directory. Look at the generated Cargo.toml file: output.txt 2>&1 cd ../../.. --> Filename: Cargo.toml [package] name = "guessing_game" version = "0.1.0" edition = "2024" [dependencies] As you saw in Chapter 1, cargo new generates a “Hello, world!” program for you. Check out the src/main.rs file: Filename: src/main.rs fn main() { println!("Hello, world!"); } Now let’s compile this “Hello, world!” program and run it in the same step using the cargo run command: $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.08s Running `target/debug/guessing_game` Hello, world! The run command comes in handy when you need to rapidly iterate on a project, as we’ll do in this game, quickly testing each iteration before moving on to the next one. Reopen the src/main.rs file. You’ll be writing all the code in this file. Processing a Guess The first part of the guessing game program will ask for user input, process that input, and check that the input is in the expected form. To start, we’ll allow the player to input a guess. Enter the code in Listing 2-1 into src/main.rs . Filename: src/main.rs use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Listing 2-1 : Code that gets a guess from the user and prints it This code contains a lot of information, so let’s go over it line by line. To obtain user input and then print the result as output, we need to bring the io input/output library into scope. The io library comes from the standard library, known as std : use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } By default, Rust has a set of items defined in the standard library that it brings into the scope of every program. This set is called the prelude , and you can see everything in it in the standard library documentation . If a type you want to use isn’t in the prelude, you have to bring that type into scope explicitly with a use statement. Using the std::io library provides you with a number of useful features, including the ability to accept user input. As you saw in Chapter 1, the main function is the entry point into the program: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } The fn syntax declares a new function; the parentheses, () , indicate there are no parameters; and the curly bracket, { , starts the body of the function. As you also learned in Chapter 1, println! is a macro that prints a string to the screen: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This code is printing a prompt stating what the game is and requesting input from the user. Storing Values with Variables Next, we’ll create a variable to store the user input, like this: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } Now the program is getting interesting! There’s a lot going on in this little line. We use the let statement to create the variable. Here’s another example: let apples = 5; This line creates a new variable named apples and binds it to the value 5 . In Rust, variables are immutable by default, meaning once we give the variable a value, the value won’t change. We’ll be discussing this concept in detail in the “Variables and Mutability” section in Chapter 3. To make a variable mutable, we add mut before the variable name: let apples = 5; // immutable let mut bananas = 5; // mutable Note: The // syntax starts a comment that continues until the end of the line. Rust ignores everything in comments. We’ll discuss comments in more detail in Chapter 3 . Returning to the guessing game program, you now know that let mut guess will introduce a mutable variable named guess . The equal sign ( = ) tells Rust we want to bind something to the variable now. On the right of the equal sign is the value that guess is bound to, which is the result of calling String::new , a function that returns a new instance of a String . String is a string type provided by the standard library that is a growable, UTF-8 encoded bit of text. The :: syntax in the ::new line indicates that new is an associated function of the String type. An associated function is a function that’s implemented on a type, in this case String . This new function creates a new, empty string. You’ll find a new function on many types because it’s a common name for a function that makes a new value of some kind. In full, the let mut guess = String::new(); line has created a mutable variable that is currently bound to a new, empty instance of a String . Whew! Receiving User Input Recall that we included the input/output functionality from the standard library with use std::io; on the first line of the program. Now we’ll call the stdin function from the io module, which will allow us to handle user input: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } If we hadn’t imported the io module with use std::io; at the beginning of the program, we could still use the function by writing this function call as std::io::stdin . The stdin function returns an instance of std::io::Stdin , which is a type that represents a handle to the standard input for your terminal. Next, the line .read_line(&mut guess) calls the read_line method on the standard input handle to get input from the user. We’re also passing &mut guess as the argument to read_line to tell it what string to store the user input in. The full job of read_line is to take whatever the user types into standard input and append that into a string (without overwriting its contents), so we therefore pass that string as an argument. The string argument needs to be mutable so that the method can change the string’s content. The & indicates that this argument is a reference , which gives you a way to let multiple parts of your code access one piece of data without needing to copy that data into memory multiple times. References are a complex feature, and one of Rust’s major advantages is how safe and easy it is to use references. You don’t need to know a lot of those details to finish this program. For now, all you need to know is that, like variables, references are immutable by default. Hence, you need to write &mut guess rather than &guess to make it mutable. (Chapter 4 will explain references more thoroughly.) Handling Potential Failure with Result We’re still working on this line of code. We’re now discussing a third line of text, but note that it’s still part of a single logical line of code. The next part is this method: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } We could have written this code as: io::stdin().read_line(&mut guess).expect("Failed to read line"); However, one long line is difficult to read, so it’s best to divide it. It’s often wise to introduce a newline and other whitespace to help break up long lines when you call a method with the .method_name() syntax. Now let’s discuss what this line does. As mentioned earlier, read_line puts whatever the user enters into the string we pass to it, but it also returns a Result value. Result is an enumeration , often called an enum , which is a type that can be in one of multiple possible states. We call each possible state a variant . Chapter 6 will cover enums in more detail. The purpose of these Result types is to encode error-handling information. Result ’s variants are Ok and Err . The Ok variant indicates the operation was successful, and it contains the successfully generated value. The Err variant means the operation failed, and it contains information about how or why the operation failed. Values of the Result type, like values of any type, have methods defined on them. An instance of Result has an expect method that you can call. If this instance of Result is an Err value, expect will cause the program to crash and display the message that you passed as an argument to expect . If the read_line method returns an Err , it would likely be the result of an error coming from the underlying operating system. If this instance of Result is an Ok value, expect will take the return value that Ok is holding and return just that value to you so that you can use it. In this case, that value is the number of bytes in the user’s input. If you don’t call expect , the program will compile, but you’ll get a warning: $ cargo build Compiling guessing_game v0.1.0 (file:///projects/guessing_game) warning: unused `Result` that must be used --> src/main.rs:10:5 | 10 | io::stdin().read_line(&mut guess); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this `Result` may be an `Err` variant, which should be handled = note: `#[warn(unused_must_use)]` on by default help: use `let _ = ...` to ignore the resulting value | 10 | let _ = io::stdin().read_line(&mut guess); | +++++++ warning: `guessing_game` (bin "guessing_game") generated 1 warning Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.59s Rust warns that you haven’t used the Result value returned from read_line , indicating that the program hasn’t handled a possible error. The right way to suppress the warning is to actually write error-handling code, but in our case we just want to crash this program when a problem occurs, so we can use expect . You’ll learn about recovering from errors in Chapter 9 . Printing Values with println! Placeholders Aside from the closing curly bracket, there’s only one more line to discuss in the code so far: use std::io; fn main() { println!("Guess the number!"); println!("Please input your guess."); let mut guess = String::new(); io::stdin() .read_line(&mut guess) .expect("Failed to read line"); println!("You guessed: {guess}"); } This line prints the string that now contains the user’s input. The {} set of curly brackets is a placeholder: Think of {} as little crab pincers that hold a value in place. When printing the value of a variable, the variable name can go inside the curly brackets. When printing the result of evaluating an expression, place empty curly brackets in the format string, then follow the format string with a comma-separated list of expressions to print in each empty curly bracket placeholder in the same order. Printing a variable and the result of an expression in one call to println! would look like this: #![allow(unused)] fn main() { let x = 5; let y = 10; println!("x = {x} and y + 2 = {}", y + 2); } This code would print x = 5 and y + 2 = 12 . Testing the First Part Let’s test the first part of the guessing game. Run it using cargo run : $ cargo run Compiling guessing_game v0.1.0 (file:///projects/guessing_game) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.44s Running `target/debug/guessing_game` Guess the number! Please input your guess. 6 You guessed: 6 At this point, the first part of the game is done: We’re getting input from the keyboard and then printing it. Generating a Secret Number Next, we need to generate a secret number that the user will try to guess. The secret number should be different every time so that the game is fun to play more than once. We’ll use a random number between 1 and 100 so that the game isn’t too difficult. Rust doesn’t yet include random number | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/decisions/?trk=products_seo_search | Decisions | LinkedIn Skip to main content LinkedIn Decisions in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Decisions Business Process Management Software by Decisions See who's skilled in this Add as skill Learn more Report this product About Decisions empowers people to automate everything and be free of inefficient, revenue-draining manual processes. Our no-code, rules-driven process automation platform enables both business and IT departments to unlock growth, increase profitability, and protect their brand. Media Products media viewer No more previous content Workflow Designer The Decisions flow designer allows creation of graphical models that are able to be executed. Flows can be started by user interaction (forms), on a schedule or based on an api call or event Statement Rules Statement rules can result in a a simple decision (true/false), trigger an action or return a value. Rules are designed in a step by step editor (without writing code). Form Designer The form designer is a graphical drag and drop tool that allows creation of forms in a WYSIWYG fashion. Forms can be laid out in a variety of layouts and can take advantage of CSS for styling. Forms can be dynamic with rules for control showing/hiding, custom validation rules, etc. Report Designer The report writer and page designer allow the creation of end user reports and dashboards that allow data to be viewed and acted on. This designer works on the basis of 'data sources' that enable the designer user to configure data access without writing sql. Reports can report on data that is in other sources, not only database stored data. No more next content Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fstratsys-strategic-planning%3FviewConnections%3Dtrue&trk=products_details_guest_face-pile-cta | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fdataport-a%C3%B6r-dprojecttracking%3FviewConnections%3Dtrue&trk=products_details_guest_face-pile-cta | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://visualstudio.microsoft.com/pt-br/vs/ | IDE do Visual Studio 2022 – IA para codificação, depuração e teste Pular para o conteúdo principal Microsoft Visual Studio Visual Studio Visual Studio Início Ferramentas para Desenvolvedores Visual Studio Visual Studio Visão geral Recursos Edições Extensões Introdução Status do Serviço Suporte a Perguntas Frequentes Documentação Blog Visual Studio Code Visual Studio Code Visão geral Extensões Suporte Documentação Blog VS Code for Education Downloads Comprar Assinaturas Visão geral Suporte Portal do Administrador Portal do Assinante Dev Essentials Visual Studio Hub Mais Visual Studio Gratuito Toda a Microsoft Global Segurança da Microsoft Azure Dynamics 365 Microsoft 365 Microsoft Teams Windows 365 Tecnologia e inovação Tecnologia e inovação IA Espaço do Azure Realidade misturada Microsoft HoloLens Microsoft Viva Computação quântica Sustentabilidade Setores Setores Educação Automotivo Serviços financeiros Governo Saúde Manufatura Varejo Todos os setores Parceiros Parceiros Encontrar um parceiro Seja um parceiro Partner Network Microsoft Marketplace Marketplace Rewards Software development companies Recursos Recursos Blog Microsoft Advertising Centro do desenvolvedor Documentação Eventos Licenciamento Microsoft Learn Microsoft Research Ver mapa do site Entrar This device is not currently supported for these products. Visual Studio IDE Visual Studio for Mac Visual Studio Code To continue downloading, click here IDE do Visual Studio 2022 – IA para codificação, depuração e teste 2025-12-08T11:35:55-08:00 IDE poderosa, agora mais inteligente com IA Modo de agente — agora disponível no GitHub Copilot Free Experimente a assistência de codificação da plataforma IA analisa os problemas, coordena as próximas etapas, aplica alterações e itera sobre erros. Baixar o Visual Studio Community Professional Enterprise Insiders Comece a usar gratuitamente Assistência de IA que aumenta a produtividade Soluções reais de IA com modo agente Planeje, crie, teste e corrija, tudo a partir de um único prompt. Descreva sua necessidade em linguagem natural e deixe o Copilot fazer o resto. Execute linters, testes e comandos sem sair do Visual Studio. Ative o modo agente hoje Modelos de IA sempre atualizados Acesse os modelos de IA mais recentes para obter sugestões precisas e com reconhecimento de contexto no Chat ou embutida. Selecione um modelo que atenda às necessidades de cada tarefa. Obter os modelos mais recentes Gratuito e totalmente integrado ao Visual Studio Assistência de codificação com IA, integrada ao Visual Studio. Receba 2.000 conclusões de código. Obtenha 50 mensagens de chat gratuitas por mês. Habilitar o Copilot Free Veja o GitHub Copilot em ação Nunca mais escreva uma mensagem de commit: obrigado, GitHub Copilot Edição de múltiplos arquivos com o GitHub Copilot no Visual Studio Introdução ao GitHub Copilot Free no Visual Studio Mantenha-se atualizado com tudo sobre o Visual Studio Visite o Hub do Visual Studio Desenvolver Depurar Teste Controle de versão Colaboração Nuvem Design Perfil Dados Copilot: seu programador em par Acelere o desenvolvimento com sugestões de conclusão de código com reconhecimento de contexto para uma única linha ou um trecho de código inteiro. Use as Edições do Copilot para edição de vários arquivos com revisão de código, visualização no arquivo e experiência de reversão. Como usar o Copilot para sugestões de código Converse para obter ajuda com código e perguntas Obtenha ajuda em tempo real para suas dúvidas de codificação com o GitHub Copilot Chat. A interface de chat de conversação fornece sugestões instantâneas com reconhecimento de contexto, auxilia na depuração e gera testes de unidade, tudo dentro do seu ambiente de desenvolvimento. Dicas para melhorar os resultados do Copilot Chat Depuração facilitada com o Copilot Acelere a depuração com análises detalhadas do seu código, impulsionadas por IA. O Copilot oferece análises e explicações detalhadas para fornecer soluções específicas para exceções, deadlocks e outros cenários de depuração. Simplifique seu processo de depuração Aumente a eficiência dos testes com o Copilot Reduza o tempo gasto na criação de testes manuais e na manutenção da qualidade do código. A automação do Copilot ajuda a melhorar a confiabilidade, identificando erros antecipadamente com testes de unidade e de integração baseados no código existente. Use o Copilot para corrigir erros Aproveite o Copilot para simplificar o controle de versão Mantenha uma base de código limpa e organizada com mensagens de commit geradas por IA com base nas alterações de código. O GitHub Copilot simplifica seu controle de versão, garantindo clareza no fluxo de trabalho, no gerenciamento de branches e nos conflitos de mesclagem. Gerar mensagens de commit com o GitHub Copilot Chat Compartilhar mais do que telas Sessões de colaboração em tempo real da sua equipe do Live Share aceleram os ciclos de edição e depuração da sua equipe, independentemente do idioma ou da plataforma. Sessões personalizadas com controles de acesso e configurações personalizadas do editor garantem que todos permaneçam consistentes com o código. Colabore com o Live Share Azure no Visual Studio Compilar, implantar e escalar com o Azure no Visual Studio: Crie aplicativos voltados para a nuvem de forma eficiente e segura usando ferramentas integradas e recursos de IA, tudo dentro da sua IDE. Seja desenvolvendo aplicativos Web, APIs ou soluções com IA, o Visual Studio oferece integração fluida com o Azure para uma experiência de codificação mais simples. Explore tutoriais, eleve seu código e automatize implantações com Azure DevOps e GitHub Actions. Conecte-se a serviços do Azure, publique aplicativos e depure em tempo real com as ferramentas avançadas do Visual Studio. Saiba mais sobre o Azure no Visual Studio Projete belos aplicativos multiplataforma O Visual Studio é a melhor IDE para criar aplicativos modernos e multiplataforma para Windows, Mac, Linux, iOS e Android. Crie aplicativos cliente avançados com WinForms, WPF, WinUI e MAUI, usando designers visuais que simplificam layouts complexos e dão vida à sua interface. Visualização e modelagem Compilar aplicativos rápidos e responsivos com as ferramentas de criação de perfil internas Use as ferramentas de criação de perfil no Visual Studio para criar aplicativos .NET e C++ rápidos e responsivos para Web e cliente. Com criadores de perfil para CPU, memória, XAML, bancos de dados, eventos e muito mais, você tem um conjunto inteiro de ferramentas que ajudam a identificar e resolver problemas de desempenho. Meça o desempenho do aplicativo Ferramentas para tornar o SQL mais fácil Trabalhe com projetos SQL sem sair do IDE. Crie consultas com experiências avançadas de edição e exiba e explore servidores e bancos de dados. Visualize esquemas de banco de dados e consultas de dentro do Visual Studio. Acesso a dados no Visual Studio Torne-o seu Configure e tema exatamente como você esperava de qualquer ferramenta de desenvolvimento moderna. Se você escolher um dos temas padrão já instalados ou explorar novos temas do Visual Studio Marketplace, você terá a liberdade de tornar seu editor ou IDE realmente seu. Explorar temas Prosseguir com as extensões Extensões são complementos que personalizem e aprimoram Visual Studio, incluindo configurações, recursos ou usos extras para ferramentas existentes. Com milhares de extensões no Marketplace, você tem opções para aumentar sua produtividade e atender ao seu fluxo de trabalho. Explorar Extensões GitHub Actions Instalações Uma janela que fornece uma visão do GitHub Actions para o repositório atual da solução aberta no Visual Studio. Fornecido por @timheuer Obter a extensão Markdown Editor v2 Instalações Um Markdown editor completo com visualização dinâmica e realce de sintaxe. Dá suporte ao GitHub Flavored Markdown. Obter Extensão Pacote de temas do Visual Studio Instalações Coleção de temas populares, agora disponível para Visual Studio. Saiba mais Caixa de Ferramentas do SQLite e do SQL Server Compact Instalações Essa extensão adiciona vários recursos para ajudar seus esforços de desenvolvimento de banco de dados inserido. Obter Extensão Visual Studio Community IDE gratuita e completa para estudantes, projetos de código aberto e desenvolvedores individuais. Saiba mais Download gratuito Visual Studio Professional Ferramentas de desenvolvimento poderosas, serviços e benefícios de assinatura para uma colaboração eficiente em equipes pequenas. Saiba mais Avaliação gratuita Visual Studio Enterprise Depuração avançada, segurança corporativa, desenvolvimento assistido por IA-além de Créditos do Azure e preços de Dev/Test para a nuvem. Saiba mais Avaliação gratuita Siga-nos Dev Essentials Developer Community Blogs: Visual Studio .NET C++ Novidades Copilot para organizações Copilot para uso pessoal Microsoft 365 Explorar os produtos da Microsoft Aplicativos do Windows 11 Microsoft Store Perfil da conta Centro de Download Suporte da Microsoft Store Devoluções Acompanhamento de pedidos Educação Microsoft Education Dispositivos para educação Microsoft Teams para Educação Microsoft 365 Education Office Education Treinamento e desenvolvimento de educadores Ofertas para estudantes e pais Azure para estudantes Negócios Segurança da Microsoft Azure Dynamics 365 Microsoft 365 Microsoft Advertising Microsoft 365 Copilot Microsoft Teams Desenvolvedor e TI Desenvolvedor Microsoft Microsoft Learn Suporte para aplicativos de marketplace de IA Comunidade Microsoft Tech Microsoft Marketplace Microsoft Power Platform Marketplace Rewards Visual Studio Empresa Carreiras Sobre a Microsoft Notícias da empresa Privacidade na Microsoft Investidores Diversidade e inclusão Acessibilidade Sustentabilidade Português (Brasil) Ícone de recusa de opções de privacidade Suas opções de privacidade Ícone de recusa de opções de privacidade Suas opções de privacidade Privacidade dos Dados de Saúde do Consumidor Fale conosco Privacidade e Cookies Gerenciar cookies Termos de uso Marcas comerciais Leia sobre os nossos anúncios © Microsoft 2026 Microsoft do Brasil Importação e Comércio de Software e Vídeo Games Ltda., com sede na cidade de São Paulo, Estado de São Paulo, na Avenida Presidente Juscelino Kubitschek, nº 1.909, conjunto 181, localizado no 18º andar da Torre Sul SP Corporate Towers, Vila Nova Conceição, CEP 04543-907, inscrita no CNPJ sob o nº 04.712.500/0001-07. | 2026-01-13T09:29:16 |
https://rust-lang.github.io/rust-clippy/stable/index.html#assertions_on_constants | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=0jBP_aEAAAAJ&hl=ko&oe=ASCII | Yinzhi Cao - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 7232 5793 h-index 35 29 i10-index 60 58 0 2100 1050 525 1575 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 19 39 63 107 141 271 354 411 561 674 956 1509 2037 49 공개 액세스 모두 보기 모두 보기 자료 54개 자료 0개 공개 비공개 재정 지원 요구사항 기준 공동 저자 모두 보기 Junfeng Yang Professor of Computer Science, Columbia University cs.columbia.edu의 이메일 확인됨 Yan Chen Northwestern University northwestern.edu의 이메일 확인됨 Suman Jana Associate Professor of Computer Science, Columbia University cs.columbia.edu의 이메일 확인됨 Kexin Pei Assistant Professor, Computer Science, University of Chicago cs.uchicago.edu의 이메일 확인됨 Min Yang (杨珉) Professor, School of Computer Science and Technology, Fudan University fudan.edu.cn의 이메일 확인됨 Song Li Zhejiang University zju.edu.cn의 이메일 확인됨 Neil Zhenqiang Gong Associate Professor, Duke University duke.edu의 이메일 확인됨 Philippe Burlina Zoox (Amazon), JHU/CS jhuapl.edu의 이메일 확인됨 Yuan Zhang Professor, School of Computer Science, Fudan University fudan.edu.cn의 이메일 확인됨 Xiang Pan Google u.northwestern.edu의 이메일 확인됨 Vaibhav Rastogi Google wisc.edu의 이메일 확인됨 Xiaohan Zhang Fudan University fudan.edu.cn의 이메일 확인됨 Cihang Xie Assistant Professor, University of California, Santa Cruz ucsc.edu의 이메일 확인됨 Christopher Kruegel University of California, Santa Barbara and Cisco, Inc. cs.ucsb.edu의 이메일 확인됨 Giovanni Vigna UC Santa Barbara and VMware cs.ucsb.edu의 이메일 확인됨 VN Venkatakrishnan Professor of Computer Science, University of Illinois at Chicago uic.edu의 이메일 확인됨 Jianwei Zhuge Associate Professor, Tsinghua University cernet.edu.cn의 이메일 확인됨 Manuel Egele Boston University bu.edu의 이메일 확인됨 Yanick Fratantonio Senior Research Scientist, Google fratantonio.me의 이메일 확인됨 Antonio Bianchi Associate Professor, Purdue University purdue.edu의 이메일 확인됨 모두 보기 팔로우 Yinzhi Cao Johns Hopkins University jhu.edu의 이메일 확인됨 Computer Security 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Deepxplore: Automated whitebox testing of deep learning systems K Pei, Y Cao, J Yang, S Jana proceedings of the 26th Symposium on Operating Systems Principles, 1-18 , 2017 1930 2017 Towards making systems forget with machine unlearning Y Cao, J Yang 2015 IEEE symposium on security and privacy, 463-480 , 2015 1149 2015 Trustllm: Trustworthiness in large language models Y Huang, L Sun, H Wang, S Wu, Q Zhang, Y Li, C Gao, Y Huang, W Lyu, ... arXiv preprint arXiv:2401.05561 , 2024 640 * 2024 EdgeMiner: Automatically Detecting Implicit Control Flow Transitions through the Android Framework. Y Cao, Y Fratantonio, A Bianchi, M Egele, C Kruegel, G Vigna, Y Chen NDSS , 2015 259 2015 Enhancing state-of-the-art classifiers with api semantics to detect evolved android malware X Zhang, Y Zhang, M Zhong, D Ding, Y Cao, Y Zhang, M Zhang, M Yang Proceedings of the 2020 ACM SIGSAC conference on computer and communications�… , 2020 255 2020 Sneakyprompt: Jailbreaking text-to-image generative models Y Yang, B Hui, H Yuan, N Gong, Y Cao 2024 IEEE symposium on security and privacy (SP), 897-912 , 2024 213 2024 Practical blind membership inference attack via differential comparisons B Hui, Y Yang, H Yuan, P Burlina, NZ Gong, Y Cao Network and Distributed System Security Symposium (NDSS 2021) , 2021 180 2021 (Cross-)Browser Fingerprinting via OS and Hardware Level Features Y Cao, S Li, E Wijmans Proceedings of Network & Distributed System Security Symposium (NDSS) , 2017 180 2017 Towards practical verification of machine learning: The case of computer vision systems. K Pei, Y Cao, J Yang, S Jana arXiv preprint arXiv:1712.01785 , 2017 152 2017 Patchattack: A black-box texture-based attack with reinforcement learning C Yang, A Kortylewski, C Xie, Y Cao, A Yuille European Conference on Computer Vision, 681-698 , 2020 147 2020 PLeak: Prompt Leaking Attacks against Large Language Model Applications B Hui, H Yuan, N Gong, P Burlina, Y Cao Proceedings of the 2024 on ACM SIGSAC Conference on Computer and�… , 2024 129 2024 An ever-evolving game: Evaluation of real-world attacks and defenses in ethereum ecosystem S Zhou, Z Yang, J Xiang, Y Cao, M Yang, Y Zhang 29th {USENIX} Security Symposium ({USENIX} Security 20), 2793-2810 , 2020 87 2020 Vetting SSL usage in applications with SSLINT B He, V Rastogi, Y Cao, Y Chen, VN Venkatakrishnan, R Yang, Z Zhang 2015 IEEE Symposium on Security and Privacy, 519-534 , 2015 87 2015 Detecting node.js prototype pollution vulnerabilities via object lookup analysis S Li, M Kang, J Hou, Y Cao Proceedings of the 29th ACM Joint Meeting on European Software Engineering�… , 2021 80 2021 Mining Node.js Vulnerabilities via Object Dependence Graph and Query S Li, M Kang, J Hou, Y Cao Proceedings of the USENIX Security Symposium , 2022 74 2022 Cspautogen: Black-box enforcement of content security policy upon real-world websites X Pan, Y Cao, S Liu, Y Zhou, Y Chen, T Zhou Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications�… , 2016 74 2016 Follow the rules: Reasoning for video anomaly detection with large language models Y Yang, K Lee, B Dariush, Y Cao, SY Lo European Conference on Computer Vision, 304-322 , 2024 72 2024 FlowCog: Context-aware Semantics Extraction and Analysis of Information Flow Leaks in Android Apps X Pan, Y Cao, X Du, B He, G Fang, R Shao, Y Chen 27th USENIX Security Symposium (USENIX Security 18), 1669-1685 , 2018 72 * 2018 PathCutter: Severing the Self-Propagation Path of XSS JavaScript Worms in Social Web Networks. Y Cao, V Yegneswaran, PA Porras, Y Chen NDSS , 2012 72 2012 De-obfuscation and detection of malicious PDF files with high accuracy X Lu, J Zhuge, R Wang, Y Cao, Y Chen 2013 46th Hawaii international conference on system sciences, 4890-4899 , 2013 71 2013 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://docs.softwareheritage.org/devel/swh-model/cli.html | Command-line interface — Software Heritage documentation Skip to main content Back to top Ctrl + K Development API reference Usage Resources Infrastructure More About GitLab PyPI System Status Software Heritage Homepage Development API reference Usage Resources Infrastructure About GitLab PyPI System Status Software Heritage Homepage Section Navigation swh.alter Using swh-alter Removal algorithm Recovery bundles swh.alter package swh.alter.bech32 module swh.alter.cli module swh.alter.inventory module swh.alter.mirror_notification_watcher module swh.alter.notifications module swh.alter.operations module swh.alter.progressbar module swh.alter.recovery_bundle module swh.alter.removable module swh.alter.subgraph module swh.alter.utils module swh.auth Command-line interface Django components swh.auth package swh.auth.django package swh.auth.django.backends module swh.auth.django.middlewares module swh.auth.django.models module swh.auth.django.utils module swh.auth.django.views module swh.auth.starlette package swh.auth.starlette.backends module swh.auth.cli module swh.auth.keycloak module swh.auth.pytest_plugin module swh.auth.utils module swh.coarnotify Explanations What’s COAR Notify ? What are we doing with the metadata ? swh.coarnotify package swh.coarnotify.server package swh.coarnotify.server.management package swh.coarnotify.server.admin module swh.coarnotify.server.apps module swh.coarnotify.server.forms module swh.coarnotify.server.handlers module swh.coarnotify.server.models module swh.coarnotify.server.signals module swh.coarnotify.server.utils module swh.coarnotify.server.views module swh.coarnotify.settings package swh.coarnotify.settings.common module swh.coarnotify.settings.development module swh.coarnotify.settings.production module swh.coarnotify.settings.tests module swh.coarnotify.cli module swh.coarnotify.client module swh.coarnotify.manage module swh.coarnotify.parsers module swh.coarnotify.renderers module swh.coarnotify.tasks module swh.coarnotify.urls module How-to guides Install swh-coarnotify Access the inbox Send a mention of a software in a scientific paper References Workflows Specifications Rest API Command Line Interface Notification payloads swh.core Command-line interface Common database utilities swh.core package swh.core.api package swh.core.api.asynchronous module swh.core.api.classes module swh.core.api.gunicorn_config module swh.core.api.negotiation module swh.core.api.serializers module swh.core.cli package swh.core.cli.backend module swh.core.cli.db module swh.core.cli.nar module swh.core.cli.sentry module swh.core.db package swh.core.db.common module swh.core.db.db_utils module swh.core.github package swh.core.github.pytest_plugin module swh.core.github.utils module swh.core.s3 namespace swh.core.s3.downloader module swh.core.s3.pytest_plugin module swh.core.api_async module swh.core.collections module swh.core.config module swh.core.logger module swh.core.logging module swh.core.nar module swh.core.pytest_plugin module swh.core.retry module swh.core.sentry module swh.core.statsd module swh.core.tarball module swh.core.utils module swh.counters swh.counters package swh.counters.api package swh.counters.api.client module swh.counters.api.server module swh.counters.cli module swh.counters.history module swh.counters.in_memory module swh.counters.interface module swh.counters.journal_client module swh.counters.kafka_client module swh.counters.redis module swh.dataportal How to guides How to use the CLI References Static site generation process Data used to generate the website swh.datasets Luigi workflows Command-line interface swh.datasets package swh.datasets.luigi package swh.datasets.luigi.aggregate_datasets module swh.datasets.luigi.blobs_datasets module swh.datasets.luigi.file_names module swh.datasets.luigi.impact module swh.datasets.luigi.origin_contributors module swh.datasets.cli module swh.datasets.download module swh.datasets.shell module swh.deposit Deposit API User Manual API Documentation Service document Create deposit Update content Update metadata Retrieve status Display content Deposit metadata Use cases Register account Deposit internals Running swh-deposit locally Production deployment Authentication Loading workflow Specifications Loading specification Protocol reference The metadata-only deposit swh.deposit package swh.deposit.api package swh.deposit.api.private package swh.deposit.api.collection module swh.deposit.api.common module swh.deposit.api.content module swh.deposit.api.converters module swh.deposit.api.edit module swh.deposit.api.edit_media module swh.deposit.api.service_document module swh.deposit.api.state module swh.deposit.api.sword_edit module swh.deposit.api.urls module swh.deposit.api.utils module swh.deposit.cli package swh.deposit.cli.admin module swh.deposit.cli.client module swh.deposit.fixtures package swh.deposit.loader package swh.deposit.loader.checker module swh.deposit.loader.checks module swh.deposit.loader.tasks module swh.deposit.templates package swh.deposit.templates.deposit package swh.deposit.tests_migration package swh.deposit.apps module swh.deposit.auth module swh.deposit.client module swh.deposit.config module swh.deposit.errors module swh.deposit.exception module swh.deposit.gunicorn_config module swh.deposit.manage module swh.deposit.models module swh.deposit.parsers module swh.deposit.urls module swh.deposit.utils module Command-line interface swh.digestmap Design document for a hash conversion service swh.digestmap module swh.export Software Heritage Graph Dataset Dataset Relational schema Setup on Amazon Athena Setup on Azure Databricks Exporting a dataset Exporting a subdataset swh.export package swh.export.exporters package swh.export.exporters.edges module swh.export.exporters.orc module swh.export.test namespace swh.export.test.test_edges module swh.export.test.test_journal_processor module swh.export.test.test_orc module swh.export.test.test_utils module swh.export.athena module swh.export.cli module swh.export.exporter module swh.export.fullnames module swh.export.journalprocessor module swh.export.luigi module swh.export.relational module swh.export.utils module swh.fuse Tutorial Configuration Advice for parallelization Design notes Command-line interface swh.fuse package swh.fuse.backends package swh.fuse.backends.compressed module swh.fuse.backends.objstorage module swh.fuse.backends.web_api module swh.fuse.fs namespace swh.fuse.fs.artifact module swh.fuse.fs.entry module swh.fuse.fs.mountpoint module swh.fuse.cache module swh.fuse.cli module swh.fuse.fuse module swh.graph Quickstart Graph Querying HTTP API Using the gRPC API Rust API Memory & Performance tuning Graph compression Command-line interface Docker environment git2graph Test graphs Example dataset Provenance index swh.graph namespace swh.graph.example_dataset package swh.graph.example_dataset.generate_dataset module swh.graph.grpc namespace swh.graph.grpc.swhgraph_pb2 module swh.graph.grpc.swhgraph_pb2_grpc module swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.shell module swh.graph.luigi package swh.graph.luigi.compressed_graph module swh.graph.luigi.subdataset module swh.graph.luigi.utils module swh.graph.cli module swh.graph.client module swh.graph.config module swh.graph.download module swh.graph.e2e_check module swh.graph.find_context module swh.graph.grpc_server module swh.graph.http_client module swh.graph.http_naive_client module swh.graph.http_rpc_server module swh.graph.naive_client module swh.graph.pytest_plugin module swh.graph.shell module swh.graph.webgraph module swh.graph.libs swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.luigi.topology module swh.graph.libs.shell module Software Heritage GraphQL API swh.indexer Software Heritage - Indexer Metadata workflow SwhPkg Vocabulary swh.indexer package swh.indexer.metadata_dictionary package swh.indexer.metadata_dictionary.base module swh.indexer.metadata_dictionary.cff module swh.indexer.metadata_dictionary.codemeta module swh.indexer.metadata_dictionary.composer module swh.indexer.metadata_dictionary.dart module swh.indexer.metadata_dictionary.gitea module swh.indexer.metadata_dictionary.github module swh.indexer.metadata_dictionary.maven module swh.indexer.metadata_dictionary.npm module swh.indexer.metadata_dictionary.nuget module swh.indexer.metadata_dictionary.python module swh.indexer.metadata_dictionary.ruby module swh.indexer.metadata_dictionary.utils module swh.indexer.storage package swh.indexer.storage.api package swh.indexer.storage.converters module swh.indexer.storage.db module swh.indexer.storage.exc module swh.indexer.storage.in_memory module swh.indexer.storage.interface module swh.indexer.storage.metrics module swh.indexer.storage.model module swh.indexer.storage.writer module swh.indexer.bibtex module swh.indexer.cli module swh.indexer.codemeta module swh.indexer.fossology_license module swh.indexer.indexer module swh.indexer.metadata module swh.indexer.metadata_detector module swh.indexer.mimetype module swh.indexer.namespaces module swh.indexer.origin_head module swh.indexer.rehash module Command-line interface swh.journal Software Heritage Journal clients swh.journal package swh.journal.writer package swh.journal.writer.inmemory module swh.journal.writer.interface module swh.journal.writer.kafka module swh.journal.writer.stream module swh.journal.client module swh.journal.pytest_plugin module swh.journal.serializers module swh.lister Tutorial: list the content of your favorite forge in just a few steps Tutorial: run a lister within docker-dev in just a few steps Save a forge swh.lister package swh.lister.arch package swh.lister.arch.lister module swh.lister.arch.tasks module swh.lister.aur package swh.lister.aur.lister module swh.lister.aur.tasks module swh.lister.bioconductor package swh.lister.bioconductor.lister module swh.lister.bioconductor.tasks module swh.lister.bitbucket package swh.lister.bitbucket.lister module swh.lister.bitbucket.tasks module swh.lister.bower package swh.lister.bower.lister module swh.lister.bower.tasks module swh.lister.cgit package swh.lister.cgit.lister module swh.lister.cgit.tasks module swh.lister.conda package swh.lister.conda.lister module swh.lister.conda.tasks module swh.lister.cpan package swh.lister.cpan.lister module swh.lister.cpan.tasks module swh.lister.cran package swh.lister.cran.lister module swh.lister.cran.tasks module swh.lister.crates package swh.lister.crates.lister module swh.lister.crates.tasks module swh.lister.debian package swh.lister.debian.lister module swh.lister.debian.tasks module swh.lister.dlang package swh.lister.dlang.lister module swh.lister.dlang.tasks module swh.lister.elm package swh.lister.elm.lister module swh.lister.elm.tasks module swh.lister.gitea package swh.lister.gitea.lister module swh.lister.gitea.tasks module swh.lister.github package swh.lister.github.lister module swh.lister.github.tasks module swh.lister.gitiles package swh.lister.gitiles.lister module swh.lister.gitiles.tasks module swh.lister.gitlab package swh.lister.gitlab.lister module swh.lister.gitlab.tasks module swh.lister.gitweb package swh.lister.gitweb.lister module swh.lister.gitweb.tasks module swh.lister.gnu package swh.lister.gnu.lister module swh.lister.gnu.tasks module swh.lister.gnu.tree module swh.lister.gogs package swh.lister.gogs.lister module swh.lister.gogs.tasks module swh.lister.golang package swh.lister.golang.lister module swh.lister.golang.tasks module swh.lister.hackage package swh.lister.hackage.lister module swh.lister.hackage.tasks module swh.lister.hex package swh.lister.hex.lister module swh.lister.hex.tasks module swh.lister.julia package swh.lister.julia.lister module swh.lister.julia.tasks module swh.lister.launchpad package swh.lister.launchpad.lister module swh.lister.launchpad.tasks module swh.lister.maven package swh.lister.maven.lister module swh.lister.maven.tasks module swh.lister.nixguix package swh.lister.nixguix.lister module swh.lister.nixguix.tasks module swh.lister.npm package swh.lister.npm.lister module swh.lister.npm.tasks module swh.lister.nuget package swh.lister.nuget.lister module swh.lister.nuget.tasks module swh.lister.opam package swh.lister.opam.lister module swh.lister.opam.tasks module swh.lister.packagist package swh.lister.packagist.lister module swh.lister.packagist.tasks module swh.lister.pagure package swh.lister.pagure.lister module swh.lister.pagure.tasks module swh.lister.phabricator package swh.lister.phabricator.lister module swh.lister.phabricator.tasks module swh.lister.pubdev package swh.lister.pubdev.lister module swh.lister.pubdev.tasks module swh.lister.puppet package swh.lister.puppet.lister module swh.lister.puppet.tasks module swh.lister.pypi package swh.lister.pypi.lister module swh.lister.pypi.tasks module swh.lister.rpm package swh.lister.rpm.lister module swh.lister.rpm.tasks module swh.lister.rubygems package swh.lister.rubygems.lister module swh.lister.rubygems.tasks module swh.lister.save_bulk package swh.lister.save_bulk.lister module swh.lister.save_bulk.tasks module swh.lister.sourceforge package swh.lister.sourceforge.lister module swh.lister.sourceforge.tasks module swh.lister.stagit package swh.lister.stagit.lister module swh.lister.stagit.tasks module swh.lister.tuleap package swh.lister.tuleap.lister module swh.lister.tuleap.tasks module swh.lister.cli module swh.lister.pattern module swh.lister.utils module Command-line interface swh.loader swh.loader.core VCS Loader Overview Package Loader Tutorial Package loader specifications swh.loader.core package swh.loader.core.converters module swh.loader.core.loader module swh.loader.core.metadata_fetchers module swh.loader.core.tasks module swh.loader.core.utils module Command-line interface swh.loader.bzr Software Heritage - How Bazaar/Breezy works swh.loader.bzr package swh.loader.bzr.loader module swh.loader.bzr.tasks module Software Heritage - CVS loader swh.loader.git swh.loader.git package swh.loader.git.base module swh.loader.git.converters module swh.loader.git.directory module swh.loader.git.from_disk module swh.loader.git.loader module swh.loader.git.tasks module swh.loader.git.utils module swh.loader.mercurial swh.loader.mercurial package swh.loader.mercurial.archive_extract module swh.loader.mercurial.converters module swh.loader.mercurial.directory module swh.loader.mercurial.hgutil module swh.loader.mercurial.identify module swh.loader.mercurial.loader module swh.loader.mercurial.tasks module swh.loader.mercurial.utils module swh.loader.metadata swh.loader.metadata package swh.loader.metadata.base module swh.loader.metadata.cli module swh.loader.metadata.gitea module swh.loader.metadata.github module swh.loader.metadata.journal_client module swh.loader.svn swh.loader.svn package swh.loader.svn.converters module swh.loader.svn.directory module swh.loader.svn.exception module swh.loader.svn.fast_crawler module swh.loader.svn.loader module swh.loader.svn.replay module swh.loader.svn.svn_repo module swh.loader.svn.svn_retry module swh.loader.svn.tasks module swh.loader.svn.utils module swh.model Data model SoftWare Heritage persistent IDentifiers (SWHIDs) Command-line interface swh.model package swh.model.fields package swh.model.fields.compound module swh.model.fields.hashes module swh.model.fields.simple module swh.model.cli module swh.model.collections module swh.model.discovery module swh.model.exceptions module swh.model.from_disk module swh.model.git_objects module swh.model.hashutil module swh.model.hypothesis_strategies module swh.model.merkle module swh.model.model module swh.model.swhids module swh.model.toposort module swh.model.validators module swh.objstorage Command-line interface Winery backend swh.objstorage namespace swh.objstorage.api namespace swh.objstorage.api.client module swh.objstorage.api.server module swh.objstorage.backends package swh.objstorage.backends.seaweedfs package swh.objstorage.backends.winery package swh.objstorage.backends.azure module swh.objstorage.backends.http module swh.objstorage.backends.in_memory module swh.objstorage.backends.libcloud module swh.objstorage.backends.noop module swh.objstorage.backends.pathslicing module swh.objstorage.proxies namespace swh.objstorage.proxies.readonly module swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module swh.objstorage.cli module swh.objstorage.constants module swh.objstorage.exc module swh.objstorage.factory module swh.objstorage.interface module swh.objstorage.multiplexer module swh.objstorage.objstorage module swh.objstorage.pytest_plugin module swh.objstorage.utils module swh.objstorage.replayer Command-line interface swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module Software Heritage - Provenance swh.scanner Command-line interface swh.scanner package swh.scanner.dashboard package swh.scanner.dashboard.dashboard module swh.scanner.cli module swh.scanner.config module swh.scanner.data module swh.scanner.exceptions module swh.scanner.output module swh.scanner.policy module swh.scanner.scanner module swh.scanner.setup_wizard module swh.scheduler Command-line interface Software Heritage Scheduler Simulator swh.scheduler package swh.scheduler.api package swh.scheduler.api.client module swh.scheduler.api.serializers module swh.scheduler.api.server module swh.scheduler.celery_backend package swh.scheduler.celery_backend.config module swh.scheduler.celery_backend.first_visits module swh.scheduler.celery_backend.pika_listener module swh.scheduler.celery_backend.recurrent_visits module swh.scheduler.celery_backend.runner module swh.scheduler.celery_backend.utils module swh.scheduler.cli package swh.scheduler.cli.add_forge_now module swh.scheduler.cli.admin module swh.scheduler.cli.celery_monitor module swh.scheduler.cli.config module swh.scheduler.cli.journal module swh.scheduler.cli.origin module swh.scheduler.cli.origin_utils module swh.scheduler.cli.simulator module swh.scheduler.cli.task module swh.scheduler.cli.task_type module swh.scheduler.cli.utils module swh.scheduler.simulator package swh.scheduler.simulator.common module swh.scheduler.simulator.origin_scheduler module swh.scheduler.simulator.origins module swh.scheduler.simulator.task_scheduler module swh.scheduler.sql package swh.scheduler.sql.upgrades package swh.scheduler.backend module swh.scheduler.cli_utils module swh.scheduler.exc module swh.scheduler.in_memory module swh.scheduler.interface module swh.scheduler.journal_client module swh.scheduler.model module swh.scheduler.pytest_plugin module swh.scheduler.task module swh.scheduler.utils module swh.scrubber Command-line interface swh.scrubber package swh.scrubber.base_checker module swh.scrubber.cli module swh.scrubber.db module swh.scrubber.fixer module swh.scrubber.journal_checker module swh.scrubber.objstorage_checker module swh.scrubber.origin_locator module swh.scrubber.storage_checker module swh.scrubber.utils module swh.search Command-line interface Search Query Language swh.search package swh.search.api package swh.search.api.client module swh.search.api.server module swh.search.cli module swh.search.elasticsearch module swh.search.exc module swh.search.in_memory module swh.search.interface module swh.search.journal_client module swh.search.metrics module swh.search.translator module swh.search.utils module swh.shard Read Shard format Benchmarks swh.shard package swh.shard.cli module swh.storage Extrinsic metadata specification Object Masking swh.storage package swh.storage.algos package swh.storage.algos.diff module swh.storage.algos.dir_iterators module swh.storage.algos.directory module swh.storage.algos.discovery module swh.storage.algos.origin module swh.storage.algos.revisions_walker module swh.storage.algos.snapshot module swh.storage.algos.swhid module swh.storage.api package swh.storage.api.client module swh.storage.api.serializers module swh.storage.api.server module swh.storage.cassandra package swh.storage.cassandra.common module swh.storage.cassandra.converters module swh.storage.cassandra.cql module swh.storage.cassandra.diagram module swh.storage.cassandra.migrations module swh.storage.cassandra.model module swh.storage.cassandra.schema module swh.storage.cassandra.storage module swh.storage.postgresql package swh.storage.postgresql.converters module swh.storage.postgresql.db module swh.storage.postgresql.storage module swh.storage.proxies package swh.storage.proxies.blocking package swh.storage.proxies.masking package swh.storage.proxies.buffer module swh.storage.proxies.filter module swh.storage.proxies.record_references module swh.storage.proxies.retry module swh.storage.proxies.tenacious module swh.storage.proxies.validate module swh.storage.backfill module swh.storage.cli module swh.storage.common module swh.storage.exc module swh.storage.fixer module swh.storage.in_memory module swh.storage.interface module swh.storage.metrics module swh.storage.migrate_extrinsic_metadata module swh.storage.objstorage module swh.storage.pytest_plugin module swh.storage.replay module swh.storage.utils module swh.storage.writer module Database schema Cassandra migrations Storage replayer Command-line interface swh.vault Getting started Vault API Reference swh.vault package swh.vault.api package swh.vault.api.client module swh.vault.api.serializers module swh.vault.api.server module swh.vault.cookers package swh.vault.cookers.base module swh.vault.cookers.directory module swh.vault.cookers.git_bare module swh.vault.cookers.revision_flat module swh.vault.cookers.revision_gitfast module swh.vault.cookers.utils module swh.vault.backend module swh.vault.cache module swh.vault.cli module swh.vault.cooking_tasks module swh.vault.exc module swh.vault.in_memory_backend module swh.vault.interface module swh.vault.to_disk module Command-line interface swh.web Developers Information swh-web API URLs URI scheme for swh-web Browse application URI scheme for SoftWare Hash IDentifiers (SWHIDs) Miscellaneous URLs swh.web package swh.web.add_forge_now package swh.web.add_forge_now.admin_views module swh.web.add_forge_now.api_views module swh.web.add_forge_now.apps module swh.web.add_forge_now.models module swh.web.add_forge_now.signal_receivers module swh.web.add_forge_now.urls module swh.web.add_forge_now.utils module swh.web.add_forge_now.views module swh.web.admin package swh.web.admin.apps module swh.web.admin.urls module swh.web.alter package swh.web.alter.templatetags package swh.web.alter.apps module swh.web.alter.emails module swh.web.alter.forms module swh.web.alter.models module swh.web.alter.urls module swh.web.alter.utils module swh.web.alter.views module swh.web.api package swh.web.api.views package swh.web.api.apidoc module swh.web.api.apiresponse module swh.web.api.apiurls module swh.web.api.parsers module swh.web.api.renderers module swh.web.api.serializers module swh.web.api.throttling module swh.web.api.urls module swh.web.api.utils module swh.web.archive_coverage package swh.web.archive_coverage.urls module swh.web.archive_coverage.views module swh.web.auth package swh.web.auth.apps module swh.web.auth.models module swh.web.auth.urls module swh.web.auth.utils module swh.web.auth.views module swh.web.badges package swh.web.badges.urls module swh.web.banners package swh.web.banners.urls module swh.web.banners.views module swh.web.browse package swh.web.browse.views package swh.web.browse.browseurls module swh.web.browse.identifiers module swh.web.browse.snapshot_context module swh.web.browse.urls module swh.web.browse.utils module swh.web.client package swh.web.client.cli module swh.web.client.client module swh.web.deposit package swh.web.deposit.urls module swh.web.inbound_email package swh.web.inbound_email.management package swh.web.inbound_email.apps module swh.web.inbound_email.handle_message module swh.web.inbound_email.signals module swh.web.inbound_email.urls module swh.web.inbound_email.utils module swh.web.inbound_email.views module swh.web.jslicenses package swh.web.jslicenses.urls module swh.web.mailmap package swh.web.mailmap.management package swh.web.mailmap.apps module swh.web.mailmap.models module swh.web.mailmap.urls module swh.web.mailmap.views module swh.web.metrics package swh.web.metrics.prometheus module swh.web.metrics.urls module swh.web.metrics.views module swh.web.provenance package swh.web.provenance.api_views module swh.web.provenance.apps module swh.web.provenance.urls module swh.web.save_bulk package swh.web.save_bulk.api_views module swh.web.save_bulk.apps module swh.web.save_bulk.models module swh.web.save_bulk.urls module swh.web.save_bulk.views module swh.web.save_code_now package swh.web.save_code_now.management package swh.web.save_code_now.admin_views module swh.web.save_code_now.api_views module swh.web.save_code_now.apps module swh.web.save_code_now.models module swh.web.save_code_now.origin_save module swh.web.save_code_now.origin_visit_webhook module swh.web.save_code_now.urls module swh.web.save_code_now.views module swh.web.save_origin_webhooks package swh.web.save_origin_webhooks.bitbucket module swh.web.save_origin_webhooks.generic_receiver module swh.web.save_origin_webhooks.gitea module swh.web.save_origin_webhooks.github module swh.web.save_origin_webhooks.gitlab module swh.web.save_origin_webhooks.sourceforge module swh.web.save_origin_webhooks.urls module swh.web.utils package swh.web.utils.management package swh.web.utils.archive module swh.web.utils.citation module swh.web.utils.converters module swh.web.utils.exc module swh.web.utils.highlightjs module swh.web.utils.identifiers module swh.web.utils.middlewares module swh.web.utils.origin_visits module swh.web.utils.query module swh.web.utils.swh_templatetags module swh.web.utils.typing module swh.web.utils.url_path_converters module swh.web.utils.urlsindex module swh.web.vault package swh.web.vault.api_views module swh.web.vault.urls module swh.web.webapp package swh.web.webapp.urls module swh.web.config module swh.web.gunicorn_config module swh.web.manage module swh.web.urls module swh.web.client swh.webhooks swh.webhooks package swh.webhooks.cli module swh.webhooks.interface module swh.webhooks.journal_client module swh.webhooks.svix_retry module swh.webhooks.utils module Development API reference Software Heritage - Data model Command-line interface Command-line interface # swh identify # Compute the Software Heritage persistent identifier (SWHID) for the given source code object(s). For more details about SWHIDs see: https://docs.softwareheritage.org/devel/swh-model/persistent-identifiers.html Tip: you can pass “-” to identify the content of standard input. Examples: $ swh identify fork.c kmod.c sched/deadline.c swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c $ swh identify --no-filename /usr/src/linux/kernel/ swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab $ git clone --mirror https://forge.softwareheritage.org/source/helloworld.git $ swh identify --type snapshot helloworld.git/ swh:1:snp:510aa88bdc517345d258c1fc2babcd0e1f905e93 helloworld.git Usage swh identify [ OPTIONS ] OBJECTS... Options --dereference , --no-dereference # follow (or not) symlinks for OBJECTS passed as arguments (default: follow) --filename , --no-filename # show/hide file name (default: show) -t , --type <obj_type> # type of object to identify (default: auto) Options : auto | content | directory | origin | snapshot -x , --exclude <PATTERN> # Exclude directories using glob patterns (e.g., *.git to exclude all .git directories) -v , --verify <SWHID> # reference identifier to be compared with computed one -r , --recursive # compute SWHID recursively Arguments OBJECTS # Required argument(s) previous SoftWare Heritage persistent IDentifiers (SWHIDs) next swh.model package On this page swh identify Edit This Page Show Source so the DOM is not blocked --> © Copyright 2015-2025 The Software Heritage developers. Created using Sphinx 7.4.7. Built with the PyData Sphinx Theme 0.16.1. | 2026-01-13T09:29:16 |
https://www.linkedin.com/signup/cold-join?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Femail-marketing-software&trk=products_seo_search_nav-header-join | Sign Up | LinkedIn Make the most of your professional life Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show First name Last name Keep me logged in By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Looks like you’re using Gmail, sign up faster with Google in one tap. Continue with ( not you? ) or Sign up with credential instead Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Takes less than 2 minutes Join LinkedIn to connect with people, jobs and opportunities that matter Join now Leave | 2026-01-13T09:29:16 |
https://www.linkedin.com/signup/cold-join?session_redirect=%2Fservices%2Fproducts%2Ftencentglobal-cloud-native-database-tdsqlc%2F&trk=products_details_guest_nav-header-join | Sign Up | LinkedIn Make the most of your professional life Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Keep me logged in First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:16 |
https://hardhat.org | Hardhat 3 < < < < < Hardhat 3 is now production ready. Migrate now > > > > > documentation Hardhat 3 Hardhat Ignition Hardhat VSCode plugins hardhat 2 Hardhat 3: Rust-powered Solidity tests Ethereum development environment for professionals Get started Ready to use out of the box Hardhat includes everything you need for Solidity smart contract development. Testing, deployment, code coverage, code verification, and more. Why hardhat? Run Solidity tests on a Rust-powered runtime Deploy your contracts, run Solidity tests, and debug your code on Hardhat's new runtime written in Rust for outstanding performance. Learn more about writing Solidity tests Clear errors and Solidity stack traces When transactions revert, Hardhat shows actionable errors like "Non-payable function was called with value 1," alongside detailed Solidity stack traces to pinpoint exactly where and why your code fails. Learn more about debugging Comprehensive testing approach Write unit tests in Solidity for speed and conciseness, integration tests in TypeScript for expressiveness and complexity, or fuzzing tests to push the edges. Decide on a case by case basis. Learn more about testing Multi-chain ready: Optimism's OP Stack and Base simulation support Manage multiple networks at the same time and confidently deploy on OP Stack knowing your code was tested on an accurate simulation. Learn more about simulating Base Simple and reliable deployments Define your contract instances, their operations, and Hardhat Ignition will drive the complex details and parallelize execution. Get started with Hardhat Ignition Plugin ecosystem Extend Hardhat with a composable ecosystem of plugins that add functionality and integrate your existing tools into a smooth workflow. Learn started about simulating Base TypeScript extensibility A tooling platform designed to be extended, Hardhat has all the utilities you need to address your project-specific needs. Change anything you like. Even entire built-in tasks, or just parts of them. Learn more about extending Hardhat For teams and projects of any scale From single hacker quickly iterating on a proof of concept to full blown engineering organization dealing with ad-hoc needs at scale, Hardhat adapts as your needs change Get started with plugins Flexible. Extensible. Fast. Build your software your way—without limitations. What's new in Hardhat 3 days ago Hardhat v3.1.3 This release adds support for Solidity `0.8.31+` for ARM Linux and integrates the Mocha test runner with the unified test output. Learn more 3 days ago Hardhat v2.28.3 This release increases the block gas limit to 60,000,000. Learn more 3 days ago hardhat-mocha 3.0.9 This release integrates the Mocha test runner with the unified test output. Learn more What's new in Hardhat Solidity vs. TypeScript tests: How to choose and combine in Hardhat 3 Testing is central to Ethereum smart contract development, as bugs and vulnerabilities can lead to catastrophic losses. Most projects tests contracts either in TypeScript or Solidity. With Hardhat 3, you don’t have to choose between writing all your tests in Solidity or in TypeScript — both are first-class options, they can be combined, and each brings their unique strengths. The key is knowing where each approach fits best, and how they complement one another. Solidity Tests Writing tests d Rust-powered Hardhat: Present & Future In March, we released Hardhat v2.21.0, the first version powered by our brand new Ethereum Development Runtime (EDR, for short) implemented in Rust. This was a significant change under the hood, representing the rewriting of Hardhat's largest and most complex component—its Ethereum simulation layer—in a new language. By design, this update didn’t affect the user experience beyond improving performance. In this post, we’ll explain why we built EDR, discuss its current status, and outline what’s c Secure deployments with Hardhat Ignition and Ledger hardware wallets As you may know, we recently introduced Hardhat Ignition, a declarative system for deploying smart contracts on Ethereum, which aims to… Tell me about new product features as they come out Built by Copyright 2026 Nomic Foundation | Privacy Policy Cookie Policy We use cookies to improve your experience on our website. Read More Reject all Accept all | 2026-01-13T09:29:16 |
https://uk.linkedin.com/company/320mediamatthewhussey?trk=organization_guest_main-feed-card-text | Matthew Hussey / 320 Media | LinkedIn Skip to main content LinkedIn Articles People Learning Jobs Games Sign in Create an account Matthew Hussey / 320 Media Media Production The world’s leading advice for dating and confidence. Follow View all 15 employees Report this company About us Matthew Hussey is a New York Times bestselling author, owner of 320 Media, and coach specializing in confidence and relational intelligence. His YouTube channel is number one in the world for love life advice, with over half a billion views. He writes a weekly newsletter and is the host of the podcast Love Life With Matthew Hussey. Matthew provides monthly coaching to the members of his private community at LoveLifeClub.com. Over the past fifteen years, his proven approach has inspired millions through authentic, insightful, and practical advice that not only enables them to find love but also feel confident and in control of their own happiness. Learn more about Matthew Hussey and 320 Media at MatthewHussey.com Website LoveLifeBook.com External link for Matthew Hussey / 320 Media Industry Media Production Company size 11-50 employees Headquarters London Type Privately Held Locations 43 BERKELEY SQ London, W1J 5AP, GB Get directions Employees at Matthew Hussey / 320 Media Matthew Hussey Daniel Hyde DAVID KIRK Lauren McNeill See all employees Updates Matthew Hussey / 320 Media reposted this Celia Bradfield 1mo Report this post Matthew Hussey / 320 Media is looking for a Social Media Moderator & Editor to join our team on a short term contract this January 🔥 If you have experience editing short form videos, creating posters using Canva templates and connecting with real people to guide them towards the help they need, we'd love to hear from you👇 Check out the ad below for details on how to apply. Social Media Moderator & Editor Matthew Hussey / 320 Media, United Kingdom 8 4 Comments Like Comment Share Matthew Hussey / 320 Media reposted this Matthew Hussey 1mo Report this post New York City just ranked as the 5th WORST city to find love . . . and if you live there, you probably aren’t surprised. Some people blame the sheer density of people, which has led to an epidemic of commitment-phobes and endless situationships. Dating apps seem to be broken there too. NYC also ranked as the worst in a survey rating honesty (about things such as a person’s age, job, and appearance) among online daters. But it doesn’t have to be this way. For years, so many of my viewers have asked me to create a dating app, and for everyone in NYC who feels like they’ve tried everything and nothing works, I’ve done one even better. Introducing Sync. Sync isn’t just another dating app. It’s an AI-powered matchmaker designed to help you find real, meaningful connections by getting to know who you truly are and introducing you to people you’re deeply compatible with. No endless swiping, no wasted time . . . just real connections and better dates. We’re launching a beta test in NYC, so if you live there, this is your chance to experience something truly different. You can join the waitlist and be the first to try it out by going to http://TalkToSync.com now. 30 8 Comments Like Comment Share Matthew Hussey / 320 Media 1,165 followers 10mo Report this post We're #hiring a new Technical Operations Administrator in United States. Apply today or share this post with your network. Technical Operations Administrator Matthew Hussey / 320 Media, United States Like Comment Share Matthew Hussey / 320 Media 1,165 followers 11mo Report this post We're #hiring a new Digital Marketing Manager in Florida. Apply today or share this post with your network. Digital Marketing Manager Matthew Hussey / 320 Media, Florida, United States 3 Like Comment Share Matthew Hussey / 320 Media 1,165 followers 11mo Report this post We're #hiring a new Technical Operations Administrator in United States. Apply today or share this post with your network. Technical Operations Administrator Matthew Hussey / 320 Media, United States 3 Like Comment Share Join now to see what you are missing Find people you know at Matthew Hussey / 320 Media Browse recommended jobs for you View all updates, news, and articles Join now Similar pages The Matthew Hussey Company Online Audio and Video Media 320 Media Media Production Los Angeles, California Sarum Private Office Professional Services PX3 Partners Venture Capital and Private Equity Principals Four Candles Productions Ltd Online Audio and Video Media The Hyde Gallery Retail Art Dealers How to Get the Guy Online Audio and Video Media AVATR Egypt Retail Motor Vehicles Qesm 1st 6 October, Al Jizah Gumball Advertising Services Los Angeles, California Esther Perel Mental Health Care New York, New York Show more similar pages Show fewer similar pages Browse jobs Developer jobs 33,470 open jobs Wordpress Developer jobs 2,113 open jobs Marketing Specialist jobs 7,844 open jobs Engineer jobs 79,088 open jobs Writer jobs 3,391 open jobs Web Development Manager jobs 1,857 open jobs Website Manager jobs 1,940 open jobs Advertising Specialist jobs 1,257 open jobs Content Manager jobs 8,452 open jobs Business Development Specialist jobs 8,972 open jobs User Experience Designer jobs 2,027 open jobs Show more jobs like this Show fewer jobs like this More searches More searches Developer jobs Business Development Executive jobs Sales Manager jobs Account Manager jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Matthew Hussey / 320 Media Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=1_kJPIEAAAAJ&hl=ko&oe=ASCII | John C Mitchell - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 36364 5663 h-index 99 34 i10-index 225 98 0 1700 850 425 1275 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 98 136 209 263 296 360 436 377 443 451 471 621 544 533 683 836 909 1159 1289 1478 1411 1376 1369 1335 1496 1394 1634 1517 1520 1431 1397 1281 1155 1069 1015 977 1249 1303 46 공개 액세스 모두 보기 모두 보기 자료 13개 자료 0개 공개 비공개 재정 지원 요구사항 기준 공동 저자 모두 보기 Anupam Datta Snowflake AI Research, Ex-Professor CMU snowflake.com의 이메일 확인됨 Andre Scedrov Professor of Mathematics, Professor of Computer and Information Science, University of Pennsylvania math.upenn.edu의 이메일 확인됨 patrick lincoln SRI sri.com의 이메일 확인됨 Ante Derek Associate Professor, University of Zagreb Faculty of Electrical Engineering and Computing fer.unizg.hr의 이메일 확인됨 Elie Bursztein Google & DeepMind AI Cybersecurity technical and research lead google.com의 이메일 확인됨 Arnab Roy Research Scientist, Mysten Labs cs.stanford.edu의 이메일 확인됨 Ninghui Li Professor of Computer Science, Purdue University cs.purdue.edu의 이메일 확인됨 Dan Boneh Professor of Computer Science, Stanford University cs.stanford.edu의 이메일 확인됨 Deian Stefan UC San Diego eng.ucsd.edu의 이메일 확인됨 Vitaly Shmatikov Cornell Tech cs.cornell.edu의 이메일 확인됨 Alejandro Russo Professor, Computer Science and Engineering Department, Chalmers / G�teborg University chalmers.se의 이메일 확인됨 David Mazi�res Professor of Computer Science, Stanford University nospam.scs.stanford.edu의 이메일 확인됨 dusko pavlovic Professor at University of Hawaii hawaii.edu의 이메일 확인됨 James Braun Purdue University purdue.edu의 이메일 확인됨 Stephen Freund Computer Science, Williams College cs.williams.edu의 이메일 확인됨 Ankur Taly Senior Staff Research Scientist, Google google.com의 이메일 확인됨 Kathleen Fisher Adjunct Professor of Computer Science, Tufts University eecs.tufts.edu의 이메일 확인됨 Robert Harper Professor of Computer Science, Carnegie Mellon University andrew.cmu.edu의 이메일 확인됨 Iliano Cervesato Professor of Computer Science, Carnegie Mellon University cmu.edu의 이메일 확인됨 Dawn Song Professor of Computer Science, UC Berkeley cs.berkeley.edu의 이메일 확인됨 모두 보기 팔로우 John C Mitchell Professor of Computer Science, Stanford University Stanford.edu의 이메일 확인됨 Computer security programming languages mathematical logic education 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 TRNSYS 17: A transient system simulation program, solar energy laboratory SA Klein, WA Beckman, JW Mitchell, JA Duffie, NA Duffie, TL Freeman, ... Madison, Madison, USA: University of Wisconsin , 2010 1699 * 2010 Design of a role-based trust-management framework N Li, JC Mitchell, WH Winsborough Proceedings 2002 IEEE Symposium on Security and Privacy, 114-130 , 2002 1127 2002 Architectural support for copy and tamper resistant software D Lie, C Thekkath, M Mitchell, P Lincoln, D Boneh, J Mitchell, M Horowitz Acm Sigplan Notices 35 (11), 168-177 , 2000 1083 2000 Foundations for programming languages JC Mitchell MIT press , 1996 1004 1996 Third-party web tracking: Policy and technology JR Mayer, JC Mitchell IEEE Symp Security and Privacy, 413-427 , 2012 865 2012 Abstract types have existential type JC Mitchell, GD Plotkin ACM Transactions on Programming Languages and Systems (TOPLAS) 10 (3), 470-502 , 1988 797 1988 Automated analysis of cryptographic protocols using murphi JC Mitchell, M Mitchell, U Stern Proceedings. 1997 IEEE Symposium on Security and Privacy, 141-151 , 1997 787 1997 Client-side defense against web-based identity theft N Chou, R Ledesma, Y Teraguchi, JC Mitchell Network and Distributed Systems Security (NDSS) , 2004 727 * 2004 Robust defenses for cross-site request forgery A Barth, C Jackson, JC Mitchell Proc ACM Conf on Computer and Communications Security, 75-88 , 2008 699 2008 Privacy and contextual integrity: Framework and applications A Barth, A Datta, JC Mitchell, H Nissenbaum 2006 IEEE symposium on security and privacy (S&P'06), 15 pp.-198 , 2006 659 2006 Trustllm: Trustworthiness in large language models L Sun, Y Huang, H Wang, S Wu, Q Zhang, C Gao, Y Huang, W Lyu, ... International Conference on Machine Learning (ICML'24) , 2024 640 * 2024 Stronger Password Authentication Using Browser Extensions. B Ross, C Jackson, N Miyake, D Boneh, JC Mitchell USENIX Security Symposium 17, 32 , 2005 585 2005 Distributed credential chain discovery in trust management N Li, WH Winsborough, JC Mitchell Proceedings of the 8th ACM Conference on Computer and Communications�… , 2001 583 2001 F-bounded polymorphism for object-oriented programming P Canning, W Cook, W Hill, W Olthoff, JC Mitchell Proceedings of the fourth international conference on functional programming�… , 1989 551 * 1989 State of the art: Automated black-box web application vulnerability testing J Bau, E Bursztein, D Gupta, JC Mitchell IEEE Symposium on Security and Privacy, 332-345 , 2010 549 2010 Text-based CAPTCHA strengths and weaknesses E Bursztein, M Martin, J Mitchell Proceedings of the 18th ACM conference on Computer and communications�… , 2011 513 2011 Decision problems for propositional linear logic P Lincoln, J Mitchell, A Scedrov, N Shankar Annals of pure and applied logic 56 (1-3), 239-311 , 1992 424 1992 Type systems for programming languages JC Mitchell Formal Models and Semantics, 365-458 , 1990 418 1990 Practical declarative network management TL Hinrichs, NS Gude, M Casado, JC Mitchell, S Shenker Proceedings of the 1st ACM workshop on Research on enterprise networking, 1-10 , 2009 408 2009 Undecidability of bounded security protocols N Durgin, P Lincoln, J Mitchell, A Scedrov Workshop on formal methods and security protocols , 1999 403 1999 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
https://docs.softwareheritage.org/devel/index.html | Development — Software Heritage documentation Skip to main content Back to top Ctrl + K Development API reference Usage Resources Infrastructure More About GitLab PyPI System Status Software Heritage Homepage Development API reference Usage Resources Infrastructure About GitLab PyPI System Status Software Heritage Homepage Section Navigation Getting started Run your own Software Heritage Developer setup Docker environment Getting Started with the Software Heritage API Software Architecture Software Architecture Overview Alterations of the Software Architecture Archive Metadata workflow and architecture Citation workflow and architecture Object Storage Overview Contributing Submitting code to SWH Code review Python style guide Git style guide Sphinx gotchas Tutorial: Best practices when writing SWH docs Tutorials Software testing guide Issue debugging and monitoring guide Add a new package Frequently Asked Questions Roadmap 2025 Current and past roadmaps Roadmap 2025 Roadmap 2024 Roadmap 2023 Roadmap 2022 Roadmap 2021 Configuration reference API reference swh.alter Using swh-alter Removal algorithm Recovery bundles swh.alter package swh.alter.bech32 module swh.alter.cli module swh.alter.inventory module swh.alter.mirror_notification_watcher module swh.alter.notifications module swh.alter.operations module swh.alter.progressbar module swh.alter.recovery_bundle module swh.alter.removable module swh.alter.subgraph module swh.alter.utils module swh.auth Command-line interface Django components swh.auth package swh.auth.django package swh.auth.starlette package swh.auth.cli module swh.auth.keycloak module swh.auth.pytest_plugin module swh.auth.utils module swh.coarnotify Explanations What’s COAR Notify ? What are we doing with the metadata ? swh.coarnotify package swh.coarnotify.server package swh.coarnotify.settings package swh.coarnotify.cli module swh.coarnotify.client module swh.coarnotify.manage module swh.coarnotify.parsers module swh.coarnotify.renderers module swh.coarnotify.tasks module swh.coarnotify.urls module How-to guides Install swh-coarnotify Access the inbox Send a mention of a software in a scientific paper References Workflows Specifications Rest API Command Line Interface Notification payloads swh.core Command-line interface Common database utilities swh.core package swh.core.api package swh.core.cli package swh.core.db package swh.core.github package swh.core.s3 namespace swh.core.api_async module swh.core.collections module swh.core.config module swh.core.logger module swh.core.logging module swh.core.nar module swh.core.pytest_plugin module swh.core.retry module swh.core.sentry module swh.core.statsd module swh.core.tarball module swh.core.utils module swh.counters swh.counters package swh.counters.api package swh.counters.cli module swh.counters.history module swh.counters.in_memory module swh.counters.interface module swh.counters.journal_client module swh.counters.kafka_client module swh.counters.redis module swh.dataportal How to guides How to use the CLI References Static site generation process Data used to generate the website swh.datasets Luigi workflows Command-line interface swh.datasets package swh.datasets.luigi package swh.datasets.cli module swh.datasets.download module swh.datasets.shell module swh.deposit Deposit API User Manual API Documentation Deposit metadata Use cases Register account Deposit internals Running swh-deposit locally Production deployment Authentication Loading workflow Specifications Loading specification Protocol reference The metadata-only deposit swh.deposit package swh.deposit.api package swh.deposit.cli package swh.deposit.fixtures package swh.deposit.loader package swh.deposit.templates package swh.deposit.tests_migration package swh.deposit.apps module swh.deposit.auth module swh.deposit.client module swh.deposit.config module swh.deposit.errors module swh.deposit.exception module swh.deposit.gunicorn_config module swh.deposit.manage module swh.deposit.models module swh.deposit.parsers module swh.deposit.urls module swh.deposit.utils module Command-line interface swh.digestmap Design document for a hash conversion service swh.digestmap module swh.export Software Heritage Graph Dataset Dataset Relational schema Setup on Amazon Athena Setup on Azure Databricks Exporting a dataset Exporting a subdataset swh.export package swh.export.exporters package swh.export.test namespace swh.export.athena module swh.export.cli module swh.export.exporter module swh.export.fullnames module swh.export.journalprocessor module swh.export.luigi module swh.export.relational module swh.export.utils module swh.fuse Tutorial Configuration Advice for parallelization Design notes Command-line interface swh.fuse package swh.fuse.backends package swh.fuse.fs namespace swh.fuse.cache module swh.fuse.cli module swh.fuse.fuse module swh.graph Quickstart Graph Querying HTTP API Using the gRPC API Rust API Memory & Performance tuning Graph compression Command-line interface Docker environment git2graph Test graphs Example dataset Provenance index swh.graph namespace swh.graph.example_dataset package swh.graph.grpc namespace swh.graph.libs package swh.graph.luigi package swh.graph.cli module swh.graph.client module swh.graph.config module swh.graph.download module swh.graph.e2e_check module swh.graph.find_context module swh.graph.grpc_server module swh.graph.http_client module swh.graph.http_naive_client module swh.graph.http_rpc_server module swh.graph.naive_client module swh.graph.pytest_plugin module swh.graph.shell module swh.graph.webgraph module swh.graph.libs swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.shell module Software Heritage GraphQL API swh.indexer Software Heritage - Indexer Metadata workflow SwhPkg Vocabulary swh.indexer package swh.indexer.metadata_dictionary package swh.indexer.storage package swh.indexer.bibtex module swh.indexer.cli module swh.indexer.codemeta module swh.indexer.fossology_license module swh.indexer.indexer module swh.indexer.metadata module swh.indexer.metadata_detector module swh.indexer.mimetype module swh.indexer.namespaces module swh.indexer.origin_head module swh.indexer.rehash module Command-line interface swh.journal Software Heritage Journal clients swh.journal package swh.journal.writer package swh.journal.client module swh.journal.pytest_plugin module swh.journal.serializers module swh.lister Tutorial: list the content of your favorite forge in just a few steps Tutorial: run a lister within docker-dev in just a few steps Save a forge swh.lister package swh.lister.arch package swh.lister.aur package swh.lister.bioconductor package swh.lister.bitbucket package swh.lister.bower package swh.lister.cgit package swh.lister.conda package swh.lister.cpan package swh.lister.cran package swh.lister.crates package swh.lister.debian package swh.lister.dlang package swh.lister.elm package swh.lister.gitea package swh.lister.github package swh.lister.gitiles package swh.lister.gitlab package swh.lister.gitweb package swh.lister.gnu package swh.lister.gogs package swh.lister.golang package swh.lister.hackage package swh.lister.hex package swh.lister.julia package swh.lister.launchpad package swh.lister.maven package swh.lister.nixguix package swh.lister.npm package swh.lister.nuget package swh.lister.opam package swh.lister.packagist package swh.lister.pagure package swh.lister.phabricator package swh.lister.pubdev package swh.lister.puppet package swh.lister.pypi package swh.lister.rpm package swh.lister.rubygems package swh.lister.save_bulk package swh.lister.sourceforge package swh.lister.stagit package swh.lister.tuleap package swh.lister.cli module swh.lister.pattern module swh.lister.utils module Command-line interface swh.loader swh.loader.core VCS Loader Overview Package Loader Tutorial Package loader specifications swh.loader.core package Command-line interface swh.loader.bzr Software Heritage - How Bazaar/Breezy works swh.loader.bzr package Software Heritage - CVS loader swh.loader.git swh.loader.git package swh.loader.mercurial swh.loader.mercurial package swh.loader.metadata swh.loader.metadata package swh.loader.svn swh.loader.svn package swh.model Data model SoftWare Heritage persistent IDentifiers (SWHIDs) Command-line interface swh.model package swh.model.fields package swh.model.cli module swh.model.collections module swh.model.discovery module swh.model.exceptions module swh.model.from_disk module swh.model.git_objects module swh.model.hashutil module swh.model.hypothesis_strategies module swh.model.merkle module swh.model.model module swh.model.swhids module swh.model.toposort module swh.model.validators module swh.objstorage Command-line interface Winery backend swh.objstorage namespace swh.objstorage.api namespace swh.objstorage.backends package swh.objstorage.proxies namespace swh.objstorage.replayer package swh.objstorage.cli module swh.objstorage.constants module swh.objstorage.exc module swh.objstorage.factory module swh.objstorage.interface module swh.objstorage.multiplexer module swh.objstorage.objstorage module swh.objstorage.pytest_plugin module swh.objstorage.utils module swh.objstorage.replayer Command-line interface swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module Software Heritage - Provenance swh.scanner Command-line interface swh.scanner package swh.scanner.dashboard package swh.scanner.cli module swh.scanner.config module swh.scanner.data module swh.scanner.exceptions module swh.scanner.output module swh.scanner.policy module swh.scanner.scanner module swh.scanner.setup_wizard module swh.scheduler Command-line interface Software Heritage Scheduler Simulator swh.scheduler package swh.scheduler.api package swh.scheduler.celery_backend package swh.scheduler.cli package swh.scheduler.simulator package swh.scheduler.sql package swh.scheduler.backend module swh.scheduler.cli_utils module swh.scheduler.exc module swh.scheduler.in_memory module swh.scheduler.interface module swh.scheduler.journal_client module swh.scheduler.model module swh.scheduler.pytest_plugin module swh.scheduler.task module swh.scheduler.utils module swh.scrubber Command-line interface swh.scrubber package swh.scrubber.base_checker module swh.scrubber.cli module swh.scrubber.db module swh.scrubber.fixer module swh.scrubber.journal_checker module swh.scrubber.objstorage_checker module swh.scrubber.origin_locator module swh.scrubber.storage_checker module swh.scrubber.utils module swh.search Command-line interface Search Query Language swh.search package swh.search.api package swh.search.cli module swh.search.elasticsearch module swh.search.exc module swh.search.in_memory module swh.search.interface module swh.search.journal_client module swh.search.metrics module swh.search.translator module swh.search.utils module swh.shard Read Shard format Benchmarks swh.shard package swh.shard.cli module swh.storage Extrinsic metadata specification Object Masking swh.storage package swh.storage.algos package swh.storage.api package swh.storage.cassandra package swh.storage.postgresql package swh.storage.proxies package swh.storage.backfill module swh.storage.cli module swh.storage.common module swh.storage.exc module swh.storage.fixer module swh.storage.in_memory module swh.storage.interface module swh.storage.metrics module swh.storage.migrate_extrinsic_metadata module swh.storage.objstorage module swh.storage.pytest_plugin module swh.storage.replay module swh.storage.utils module swh.storage.writer module Database schema Cassandra migrations Storage replayer Command-line interface swh.vault Getting started Vault API Reference swh.vault package swh.vault.api package swh.vault.cookers package swh.vault.backend module swh.vault.cache module swh.vault.cli module swh.vault.cooking_tasks module swh.vault.exc module swh.vault.in_memory_backend module swh.vault.interface module swh.vault.to_disk module Command-line interface swh.web Developers Information swh-web API URLs URI scheme for swh-web Browse application URI scheme for SoftWare Hash IDentifiers (SWHIDs) Miscellaneous URLs swh.web package swh.web.add_forge_now package swh.web.admin package swh.web.alter package swh.web.api package swh.web.archive_coverage package swh.web.auth package swh.web.badges package swh.web.banners package swh.web.browse package swh.web.client package swh.web.deposit package swh.web.inbound_email package swh.web.jslicenses package swh.web.mailmap package swh.web.metrics package swh.web.provenance package swh.web.save_bulk package swh.web.save_code_now package swh.web.save_origin_webhooks package swh.web.utils package swh.web.vault package swh.web.webapp package swh.web.config module swh.web.gunicorn_config module swh.web.manage module swh.web.urls module swh.web.client swh.webhooks swh.webhooks package swh.webhooks.cli module swh.webhooks.interface module swh.webhooks.journal_client module swh.webhooks.svix_retry module swh.webhooks.utils module Archive ChangeLog Journal Specification Statsd metrics and Grafana dashboards Development Development # Getting started # Run your own Software Heritage → deploy a local copy of the Software Heritage software stack in less than 5 minutes, or Developer setup → get a working development setup that allows to hack on the Software Heritage software stack Frequently Asked Questions Contributing # Submitting code to SWH → learn how to submit your code to the Software Heritage codebase Code review → rules and guidelines to review code in Software Heritage Python style guide → how to format the Python code you write Architecture # Software Architecture Overview → get a glimpse of the Software Heritage software architecture Metadata workflow → learn how Software Heritage stores and handles metadata Data Model and Specifications # SoftWare Heritage persistent IDentifiers (SWHIDs) Specifications of the SoftWare Hash persistent IDentifiers (SWHID). Data model Documentation of the main Software Heritage archive data model. Journal Specification Documentation of the Kafka journal of the Software Heritage archive. Tutorials # Software testing guide Issue debugging and monitoring guide Listing the content of your favorite forge and running a lister in Docker Add a new swh package Tutorial: Best practices when writing SWH docs Roadmap # Current roadmap: Roadmap 2025 Previous roadmaps Roadmap 2024 Roadmap 2023 Roadmap 2022 Roadmap 2021 System Administration # Network Infrastructure Description → learn what a Software Heritage mirror is and how to set up one Keycloak → learn how to use Keycloak, the authentication system used by Software Heritage ’s web interface and public APIs Components # Here is brief overview of the most relevant software components in the Software Heritage stack, in alphabetical order. For a better introduction to the architecture, see the Software Architecture Overview , which presents each of them in a didactic order. Each component name is linked to the development documentation of the corresponding Python module. swh.alter archive alteration facilities swh.auth low-level library used by modules needing keycloak authentication swh.coarnotify a COAR Notify server implementation in Django swh.core low-level utilities and helpers used by almost all other modules in the stack swh.counters service providing efficient estimates of the number of objects in the SWH archive, using Redis’s Hyperloglog swh.datasets datasets derived from periodic data dumps created by swh.export swh.deposit push-based deposit of software artifacts to the archive swh.digestmap efficient mapping of content hashes swh.docs developer documentation (used to generate this doc you are reading) swh.export public datasets and periodic data dumps of the archive released by Software Heritage swh.fuse Virtual file system to browse the Software Heritage archive, based on FUSE swh.graph Fast, compressed, in-memory representation of the archive, with tooling to generate and query it. swh.graphql GraphQL API to request archive data offering more precise and flexible queries than the REST API. swh.indexer tools and workers used to crawl the content of the archive and extract derived information from any artifact stored in it swh.journal persistent logger of changes to the archive, with publish-subscribe support swh.lister collection of listers for all sorts of source code hosting and distribution places (forges, distributions, package managers, etc.) swh.loader-core low-level loading utilities and helpers used by all other loaders swh.loader-bzr loader for Bazaar and Breezy repositories swh.loader-git loader for Git repositories swh.loader-mercurial loader for Mercurial repositories swh.loader-metadata pseudo-loader, which fetches extrinsic metadata from forges instead of software artifacts swh.loader-svn loader for Subversion repositories swh.loader-cvs loader for CVS repositories swh.model implementation of the Data model to archive source code artifacts swh.objstorage content-addressable object storage swh.objstorage.replayer Object storage replication tool swh.shard Low level management for read-only content-addressable object storage indexed with a perfect hash table swh.provenance query service for questions like: “where does this given object come from?” or “what it the oldest revision in which this object has been found?” swh.scanner source code scanner to analyze code bases and compare them with source code artifacts archived by Software Heritage swh.scheduler task manager for asynchronous/delayed tasks, used for recurrent (e.g., listing a forge, loading new stuff from a Git repository) and one-off activities (e.g., loading a specific version of a source package) swh.scrubber Tooling to check integrity of various data stores (swh.journal, swh.objstorage, swh.storage) and fix corrupt objects they contain. swh.search search engine for the archive swh.storage abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata swh.vault implementation of the vault service, allowing to retrieve parts of the archive as self-contained bundles (e.g., individual releases, entire repository snapshots, etc.) swh.web Web application(s) to browse the archive, for both interactive (HTML UI) and mechanized (REST API) use swh.web.client Python client for swh.web Dependencies # The dependency relationships among the various modules are depicted below. Dependencies among top-level Python modules (click to zoom). # Archive # Archive ChangeLog : notable changes to the archive over time previous Welcome to Software Heritage documentation next Getting started On this page Getting started Contributing Architecture Data Model and Specifications Tutorials Roadmap System Administration Components Dependencies Archive Edit This Page Show Source so the DOM is not blocked --> © Copyright 2015-2025 The Software Heritage developers. Created using Sphinx 7.4.7. Built with the PyData Sphinx Theme 0.16.1. | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Femail-marketing-software&fromSignIn=true&trk=products_seo_search_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fdataport-a%25C3%25B6r-dprojecttracking%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?fromSignIn=true&session_redirect=https%3A%2F%2Fwww.linkedin.com%2Fcompany%2Fdigitaleconomycouncil&trk=organization_guest_main-feed-card_ellipsis-menu-semaphore-sign-in-redirect&guestReportContentType=POST&_f=guest-reporting | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?modality=modality:text&p=1&sort=trending | Text Datasets – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":401131,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities Reset Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 401,131 Full-text search Edit filters Sort: Trending Active filters: text Clear all HuggingFaceFW/finetranslations Viewer • Updated 4 days ago • 3.33B • 7.34k • 143 xiuhuywh/DRIM-VisualReasonHard Viewer • Updated 4 days ago • 17.1k • 1.8k • 96 WNT3D/Ultimate-Offensive-Red-Team Viewer • Updated Aug 23, 2025 • 25.6k • 481 • 120 xiuhuywh/DRIM-ColdstartSFT Viewer • Updated 4 days ago • 44.3k • 4.93k • 84 miromind-ai/MiroVerse-v0.1 Viewer • Updated Nov 19, 2025 • 228k • 767 • 177 123olp/binance-futures-ohlcv-2018-2026 Viewer • Updated 2 days ago • 425M • 478 • 96 DatologyAI/DatBench Viewer • Updated 2 days ago • 43.5k • 286 • 68 MiniMaxAI/OctoCodingBench Viewer • Updated about 5 hours ago • 72 • 68 Salesforce/wikitext Viewer • Updated Jan 4, 2024 • 3.71M • 793k • 616 ScienceOne-AI/S1-MMAlign Viewer • Updated 8 days ago • 21.1M • 7.54k • 70 TeichAI/glm-4.7-2000x Viewer • Updated 21 days ago • 1.98k • 339 • 71 facebook/research-plan-gen Viewer • Updated 11 days ago • 22.5k • 3.61k • 272 OpenDataArena/ODA-Mixture-500k Viewer • Updated about 22 hours ago • 506k • 5.49k • 116 nvidia/embed-nemotron-dataset-v1 Viewer • Updated 1 day ago • 12.8M • 204 • 50 DatologyAI/DatBench-Full Viewer • Updated 7 days ago • 195k • 231 • 46 OpenDataArena/ODA-Math-460k Viewer • Updated 13 days ago • 460k • 4.93k • 96 tatsu-lab/alpaca Viewer • Updated May 22, 2023 • 52k • 44.6k • 889 missvector/linux-commands Viewer • Updated about 16 hours ago • 71.8k • 617 • 84 OpenDataArena/ODA-Mixture-100k Viewer • Updated 13 days ago • 101k • 3.56k • 90 Anthropic/hh-rlhf Viewer • Updated May 26, 2023 • 169k • 22.7k • 1.63k Rapidata/bananamark-dataset Viewer • Updated Dec 12, 2025 • 2.16k • 62 • 28 wikimedia/wikipedia Viewer • Updated Jan 9, 2024 • 61.6M • 74.6k • 1.12k TeichAI/claude-4.5-opus-high-reasoning-250x Viewer • Updated Nov 28, 2025 • 250 • 8.33k • 161 openmed-community/MedReason-Stenographic Viewer • Updated 4 days ago • 31.5k • 34 • 22 m-a-p/COIG-CQIA Viewer • Updated Apr 18, 2024 • 44.7k • 5.12k • 691 HuggingFaceFW/finepdfs Viewer • Updated 4 days ago • 476M • 23.2k • 711 Bingguang/HardGen Viewer • Updated 5 days ago • 17k • 281 • 65 MiniMaxAI/VIBE Viewer • Updated 21 days ago • 200 • 10.5k • 249 MLCommons/peoples_speech Viewer • Updated Nov 20, 2024 • 8.05M • 13.6k • 246 LEMAS-Project/LEMAS-Dataset-train Viewer • Updated 4 days ago • 125M • 3.62k • 15 Previous 1 2 3 ... 100 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://www.linkedin.com/checkpoint/lg/login?session_redirect=%2Fproducts%2Fhclsoftware-hcl-sametime&fromSignIn=true&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://huggingface.co/datasets?format=format%3Aarrow | Datasets in arrow – Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up 1T","label":"> 1T","type":"size_categories"}],"format":[{"id":"format:json","label":"json","type":"format"},{"id":"format:csv","label":"csv","type":"format"},{"id":"format:parquet","label":"parquet","type":"format"},{"id":"format:optimized-parquet","label":"optimized-parquet","type":"format"},{"id":"format:imagefolder","label":"imagefolder","type":"format"},{"id":"format:audiofolder","label":"soundfolder","type":"format"},{"id":"format:webdataset","label":"webdataset","type":"format"},{"id":"format:text","label":"text","type":"format"},{"id":"format:arrow","label":"arrow","type":"format"}],"benchmark":[{"id":"benchmark:official","label":"Benchmark","type":"benchmark"}]},"numItemsPerPage":30,"numTotalItems":1983,"pageIndex":0,"searchQuery":"","sortBy":""}}"> Edit Datasets filters Main Tasks Libraries Languages Licenses Other Modalities 3D Audio Document Geospatial Image Tabular Text Time-series Video Size (rows) Reset Size < 1K > 1T Format Reset Format json csv parquet optimized-parquet imagefolder soundfolder webdataset text arrow Evaluation Benchmark Apply filters Datasets 1,983 Full-text search Edit filters Sort: Trending Active filters: arrow Clear all pnnbao-ump/VieNeu-TTS-1000h Viewer • Updated Nov 25, 2025 • 421k • 89 • 11 ccmusic-database/acapella Viewer • Updated Feb 17, 2025 • 132 • 261 • 33 sentence-transformers/quantized-retrieval-data Viewer • Updated 8 days ago • 40.7M • 130 • 2 ccmusic-database/music_genre Viewer • Updated Mar 21, 2025 • 36.4k • 473 • 63 davidmunechika/midjourney Viewer • Updated Aug 4, 2023 • 1k • 44 • 2 Salesforce/lotsa_data Viewer • Updated Jan 21, 2025 • 3.97M • 16.2k • 92 MITLL/LADI-v2-dataset Viewer • Updated Jun 25, 2024 • 9.18k • 332 • 6 mohres/The_Arabic_E-Book_Corpus Viewer • Updated Jun 9, 2024 • 1.75k • 29 • 2 MohamedRashad/arabic-books Viewer • Updated Nov 28, 2024 • 8.65k • 11.7k • 1 laion/laions_got_talent_with_voice_emotion_speed_tags_for_orpheus_tuning Viewer • Updated Apr 4, 2025 • 2.51M • 1.59k • 6 chrisjob1021/gpt2_tokenized_openwebtext Viewer • Updated Apr 19, 2025 • 8.01M • 103 • 1 stepfun-ai/GEdit-Bench Viewer • Updated Apr 29, 2025 • 1.21k • 2.23k • 26 microsoft/NextCoderDataset Viewer • Updated Jul 8, 2025 • 381k • 1.25k • 49 AuWang/PartNeXt Viewer • Updated Oct 26, 2025 • 23.5k • 247 • 11 VuSnow/Vn-OCR-Pretraining Viewer • Updated Jun 23, 2025 • 91.8k • 2.11k • 1 nvidia/AceReason-1.1-SFT Viewer • Updated Jun 18, 2025 • 3.96M • 1.73k • 95 THUIR/MemoryBench Viewer • Updated 21 days ago • 4.06k • 3.86k • 10 pnnbao-ump/VieNeu-TTS-140h Viewer • Updated Nov 18, 2025 • 73.5k • 490 • 21 86Cao/MegaPairs-Standard Viewer • Updated Nov 26, 2025 • 26.3M • 79 • 1 d3LLM/trajectory_data_llada_32 Viewer • Updated Nov 27, 2025 • 83.4k • 403 • 2 ZengXiangyu/RedPajama-Data-1T-Sample Viewer • Updated Dec 3, 2025 • 902k • 6.28k • 2 GLauzza/Mille-Pensees-Dataset Viewer • Updated Dec 8, 2025 • 77.6k • 24 • 1 mrfakename/blended-audio-data Viewer • Updated Dec 7, 2025 • 119k • 1 • 1 haykgrigorian/TimeCapsuleLLM-London-1800-1875-v2-15GB Viewer • Updated 26 days ago • 110k • 203 • 1 postgrammar/london-llm-1800 Viewer • Updated 22 days ago • 11.6M • 41 • 2 panitsasi/FedJam Viewer • Updated 2 days ago • 35.6k • 110 • 1 Qistinasofea/floorplan-aligned-strict Viewer • Updated 3 days ago • 7.39k • 34 • 1 vasudevgupta/natural-questions-validation Viewer • Updated May 4, 2021 • 7.83k • 41 TomTBT/pmc_open_access_xml Viewer • Updated Sep 15, 2024 • 5.64M • 573 • 6 SamuelYang/wikipedia_20200501.en Viewer • Updated Aug 20, 2022 • 1.66M • 54 Previous 1 2 3 ... 67 Next System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fstratsys-strategic-planning%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://uk.linkedin.com/company/320mediamatthewhussey?trk=organization_guest_main-feed-card_feed-reaction-header | Matthew Hussey / 320 Media | LinkedIn Skip to main content LinkedIn Articles People Learning Jobs Games Sign in Join for free Matthew Hussey / 320 Media Media Production The world’s leading advice for dating and confidence. Follow Discover all 15 employees Report this company About us Matthew Hussey is a New York Times bestselling author, owner of 320 Media, and coach specializing in confidence and relational intelligence. His YouTube channel is number one in the world for love life advice, with over half a billion views. He writes a weekly newsletter and is the host of the podcast Love Life With Matthew Hussey. Matthew provides monthly coaching to the members of his private community at LoveLifeClub.com. Over the past fifteen years, his proven approach has inspired millions through authentic, insightful, and practical advice that not only enables them to find love but also feel confident and in control of their own happiness. Learn more about Matthew Hussey and 320 Media at MatthewHussey.com Website LoveLifeBook.com External link for Matthew Hussey / 320 Media Industry Media Production Company size 11-50 employees Headquarters London Type Privately Held Locations 43 BERKELEY SQ London, W1J 5AP, GB Get directions Employees at Matthew Hussey / 320 Media Matthew Hussey Daniel Hyde DAVID KIRK Lauren McNeill See all employees Updates Matthew Hussey / 320 Media reposted this Celia Bradfield 1mo Report this post Matthew Hussey / 320 Media is looking for a Social Media Moderator & Editor to join our team on a short term contract this January 🔥 If you have experience editing short form videos, creating posters using Canva templates and connecting with real people to guide them towards the help they need, we'd love to hear from you👇 Check out the ad below for details on how to apply. Social Media Moderator & Editor Matthew Hussey / 320 Media, United Kingdom 8 4 Comments Like Comment Share Matthew Hussey / 320 Media reposted this Matthew Hussey 1mo Report this post New York City just ranked as the 5th WORST city to find love . . . and if you live there, you probably aren’t surprised. Some people blame the sheer density of people, which has led to an epidemic of commitment-phobes and endless situationships. Dating apps seem to be broken there too. NYC also ranked as the worst in a survey rating honesty (about things such as a person’s age, job, and appearance) among online daters. But it doesn’t have to be this way. For years, so many of my viewers have asked me to create a dating app, and for everyone in NYC who feels like they’ve tried everything and nothing works, I’ve done one even better. Introducing Sync. Sync isn’t just another dating app. It’s an AI-powered matchmaker designed to help you find real, meaningful connections by getting to know who you truly are and introducing you to people you’re deeply compatible with. No endless swiping, no wasted time . . . just real connections and better dates. We’re launching a beta test in NYC, so if you live there, this is your chance to experience something truly different. You can join the waitlist and be the first to try it out by going to http://TalkToSync.com now. 30 8 Comments Like Comment Share Matthew Hussey / 320 Media 1,165 followers 10mo Report this post We're #hiring a new Technical Operations Administrator in United States. Apply today or share this post with your network. Technical Operations Administrator Matthew Hussey / 320 Media, United States Like Comment Share Matthew Hussey / 320 Media 1,165 followers 11mo Report this post We're #hiring a new Digital Marketing Manager in Florida. Apply today or share this post with your network. Digital Marketing Manager Matthew Hussey / 320 Media, Florida, United States 3 Like Comment Share Matthew Hussey / 320 Media 1,165 followers 11mo Report this post We're #hiring a new Technical Operations Administrator in United States. Apply today or share this post with your network. Technical Operations Administrator Matthew Hussey / 320 Media, United States 3 Like Comment Share Join now to see what you are missing Find people you know at Matthew Hussey / 320 Media Browse recommended jobs for you View all updates, news, and articles Join now Similar pages The Matthew Hussey Company Online Audio and Video Media 320 Media Media Production Los Angeles, California Sarum Private Office Professional Services PX3 Partners Venture Capital and Private Equity Principals Four Candles Productions Ltd Online Audio and Video Media The Hyde Gallery Retail Art Dealers How to Get the Guy Online Audio and Video Media AVATR Egypt Retail Motor Vehicles Qesm 1st 6 October, Al Jizah Gumball Advertising Services Los Angeles, California Esther Perel Mental Health Care New York, New York Show more similar pages Show fewer similar pages Browse jobs Developer jobs 33,470 open jobs Wordpress Developer jobs 2,113 open jobs Marketing Specialist jobs 7,844 open jobs Engineer jobs 79,088 open jobs Writer jobs 3,391 open jobs Web Development Manager jobs 1,857 open jobs Website Manager jobs 1,940 open jobs Advertising Specialist jobs 1,257 open jobs Content Manager jobs 8,452 open jobs Business Development Specialist jobs 8,972 open jobs User Experience Designer jobs 2,027 open jobs Show more jobs like this Show fewer jobs like this More searches More searches Developer jobs Business Development Executive jobs Sales Manager jobs Account Manager jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Matthew Hussey / 320 Media Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fcardano-foundation-veridian&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://ai.google.dev/gemini-api/docs/vision?lang=python#bbox | Image understanding | Gemini API | Google AI for Developers Skip to main content / English Deutsch Español – América Latina Français Indonesia Italiano Polski Português – Brasil Shqip Tiếng Việt Türkçe Русский עברית العربيّة فارسی हिंदी বাংলা ภาษาไทย 中文 – 简体 中文 – 繁體 日本語 한국어 Get API key Cookbook Community Sign in Docs API reference Gemini API Docs API reference Get API key Cookbook Community Get started Overview Quickstart API keys Libraries Interactions API Models Gemini Gemini 3 Nano Banana image generation Veo video generation Lyria music generation Imagen image generation Embeddings Robotics Pricing Rate limits Core capabilities Text Image Image generation 🍌 Image understanding Video Documents Speech and audio Speech generation Audio understanding Thinking and thought signatures Thinking Thought signatures Structured outputs Function calling Long context Tools and agents Overview Deep Research Google Search Google Maps Code execution URL context Computer Use File Search Live API Get started Capabilities Tool use Session management Ephemeral tokens Guides Batch API File input Input methods Files API Context caching OpenAI compatibility Media resolution Token counting Prompt engineering Logs and datasets Get started with logs Data logging and sharing Safety Safety settings Safety guidance Open-Source frameworks LangChain & LangGraph CrewAI LlamaIndex Vercel AI SDK Resources Migrate to Gen AI SDK Release notes Deprecations API troubleshooting Billing info Partner and library integrations Google AI Studio Quickstart Vibe code in Build mode Try out LearnLM Troubleshooting Access for Workspace users Google Cloud Platform VertexAI Gemini API OAuth authentication Policies Terms of service Available regions Additional usage polices Home Gemini API Docs Send feedback Image understanding Gemini models are built to be multimodal from the ground up, unlocking a wide range of image processing and computer vision tasks including but not limited to image captioning, classification, and visual question answering without having to train specialized ML models. Tip: In addition to their general multimodal capabilities, Gemini models (2.0 and newer) offer improved accuracy for specific use cases like object detection and segmentation , through additional training. See the Capabilities section for more details. Passing images to Gemini You can provide images as input to Gemini using two methods: Passing inline image data : Ideal for smaller files (total request size less than 20MB, including prompts). Uploading images using the File API : Recommended for larger files or for reusing images across multiple requests. Passing inline image data You can pass inline image data in the request to generateContent . You can provide image data as Base64 encoded strings or by reading local files directly (depending on the language). The following example shows how to read an image from a local file and pass it to generateContent API for processing. Python from google import genai from google.genai import types with open ( 'path/to/small-sample.jpg' , 'rb' ) as f : image_bytes = f . read () client = genai . Client () response = client . models . generate_content ( model = 'gemini-2.5-flash' , contents = [ types . Part . from_bytes ( data = image_bytes , mime_type = 'image/jpeg' , ), 'Caption this image.' ] ) print ( response . text ) JavaScript import { GoogleGenAI } from "@google/genai" ; import * as fs from "node:fs" ; const ai = new GoogleGenAI ({}); const base64ImageFile = fs . readFileSync ( "path/to/small-sample.jpg" , { encoding : "base64" , }); const contents = [ { inlineData : { mimeType : "image/jpeg" , data : base64ImageFile , }, }, { text : "Caption this image." }, ]; const response = await ai . models . generateContent ({ model : "gemini-2.5-flash" , contents : contents , }); console . log ( response . text ); Go bytes , _ := os . ReadFile ( "path/to/small-sample.jpg" ) parts := [] * genai . Part { genai . NewPartFromBytes ( bytes , "image/jpeg" ), genai . NewPartFromText ( "Caption this image." ), } contents := [] * genai . Content { genai . NewContentFromParts ( parts , genai . RoleUser ), } result , _ := client . Models . GenerateContent ( ctx , "gemini-2.5-flash" , contents , nil , ) fmt . Println ( result . Text ()) REST IMG_PATH = "/path/to/your/image1.jpg" if [[ " $( base64 --version 2>&1 ) " = * "FreeBSD" * ]] ; then B64FLAGS = "--input" else B64FLAGS = "-w0" fi curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -H 'Content-Type: application/json' \ -X POST \ -d '{ "contents": [{ "parts":[ { "inline_data": { "mime_type":"image/jpeg", "data": "' " $( base64 $B64FLAGS $IMG_PATH ) " '" } }, {"text": "Caption this image."}, ] }] }' 2 > /dev/null You can also fetch an image from a URL, convert it to bytes, and pass it to generateContent as shown in the following examples. Python from google import genai from google.genai import types import requests image_path = "https://goo.gle/instrument-img" image_bytes = requests . get ( image_path ) . content image = types . Part . from_bytes ( data = image_bytes , mime_type = "image/jpeg" ) client = genai . Client () response = client . models . generate_content ( model = "gemini-2.5-flash" , contents = [ "What is this image?" , image ], ) print ( response . text ) JavaScript import { GoogleGenAI } from "@google/genai" ; async function main () { const ai = new GoogleGenAI ({}); const imageUrl = "https://goo.gle/instrument-img" ; const response = await fetch ( imageUrl ); const imageArrayBuffer = await response . arrayBuffer (); const base64ImageData = Buffer . from ( imageArrayBuffer ). toString ( 'base64' ); const result = await ai . models . generateContent ({ model : "gemini-2.5-flash" , contents : [ { inlineData : { mimeType : 'image/jpeg' , data : base64ImageData , }, }, { text : "Caption this image." } ], }); console . log ( result . text ); } main (); Go package main import ( "context" "fmt" "os" "io" "net/http" "google.golang.org/genai" ) func main () { ctx := context . Background () client , err := genai . NewClient ( ctx , nil ) if err != nil { log . Fatal ( err ) } // Download the image. imageResp , _ := http . Get ( "https://goo.gle/instrument-img" ) imageBytes , _ := io . ReadAll ( imageResp . Body ) parts := [] * genai . Part { genai . NewPartFromBytes ( imageBytes , "image/jpeg" ), genai . NewPartFromText ( "Caption this image." ), } contents := [] * genai . Content { genai . NewContentFromParts ( parts , genai . RoleUser ), } result , _ := client . Models . GenerateContent ( ctx , "gemini-2.5-flash" , contents , nil , ) fmt . Println ( result . Text ()) } REST IMG_URL = "https://goo.gle/instrument-img" MIME_TYPE = $( curl -sIL " $IMG_URL " | grep -i '^content-type:' | awk -F ': ' '{print $2}' | sed 's/\r$//' | head -n 1 ) if [[ -z " $MIME_TYPE " || ! " $MIME_TYPE " == image/* ]] ; then MIME_TYPE = "image/jpeg" fi # Check for macOS if [[ " $( uname ) " == "Darwin" ]] ; then IMAGE_B64 = $( curl -sL " $IMG_URL " | base64 -b 0 ) elif [[ " $( base64 --version 2>&1 ) " = * "FreeBSD" * ]] ; then IMAGE_B64 = $( curl -sL " $IMG_URL " | base64 ) else IMAGE_B64 = $( curl -sL " $IMG_URL " | base64 -w0 ) fi curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -H 'Content-Type: application/json' \ -X POST \ -d '{ "contents": [{ "parts":[ { "inline_data": { "mime_type":"' " $MIME_TYPE " '", "data": "' " $IMAGE_B64 " '" } }, {"text": "Caption this image."} ] }] }' 2 > /dev/null Note: Inline image data limits your total request size (text prompts, system instructions, and inline bytes) to 20MB. For larger requests, upload image files using the File API. Files API is also more efficient for scenarios that use the same image repeatedly. Uploading images using the File API For large files or to be able to use the same image file repeatedly, use the Files API. The following code uploads an image file and then uses the file in a call to generateContent . See the Files API guide for more information and examples. Python from google import genai client = genai . Client () my_file = client . files . upload ( file = "path/to/sample.jpg" ) response = client . models . generate_content ( model = "gemini-2.5-flash" , contents = [ my_file , "Caption this image." ], ) print ( response . text ) JavaScript import { GoogleGenAI , createUserContent , createPartFromUri , } from "@google/genai" ; const ai = new GoogleGenAI ({}); async function main () { const myfile = await ai . files . upload ({ file : "path/to/sample.jpg" , config : { mimeType : "image/jpeg" }, }); const response = await ai . models . generateContent ({ model : "gemini-2.5-flash" , contents : createUserContent ([ createPartFromUri ( myfile . uri , myfile . mimeType ), "Caption this image." , ]), }); console . log ( response . text ); } await main (); Go package main import ( "context" "fmt" "os" "google.golang.org/genai" ) func main () { ctx := context . Background () client , err := genai . NewClient ( ctx , nil ) if err != nil { log . Fatal ( err ) } uploadedFile , _ := client . Files . UploadFromPath ( ctx , "path/to/sample.jpg" , nil ) parts := [] * genai . Part { genai . NewPartFromText ( "Caption this image." ), genai . NewPartFromURI ( uploadedFile . URI , uploadedFile . MIMEType ), } contents := [] * genai . Content { genai . NewContentFromParts ( parts , genai . RoleUser ), } result , _ := client . Models . GenerateContent ( ctx , "gemini-2.5-flash" , contents , nil , ) fmt . Println ( result . Text ()) } REST IMAGE_PATH = "path/to/sample.jpg" MIME_TYPE = $( file -b --mime-type " ${ IMAGE_PATH } " ) NUM_BYTES = $( wc -c < " ${ IMAGE_PATH } " ) DISPLAY_NAME = IMAGE tmp_header_file = upload-header.tmp # Initial resumable request defining metadata. # The upload url is in the response headers dump them to a file. curl "https://generativelanguage.googleapis.com/upload/v1beta/files" \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -D upload-header.tmp \ -H "X-Goog-Upload-Protocol: resumable" \ -H "X-Goog-Upload-Command: start" \ -H "X-Goog-Upload-Header-Content-Length: ${ NUM_BYTES } " \ -H "X-Goog-Upload-Header-Content-Type: ${ MIME_TYPE } " \ -H "Content-Type: application/json" \ -d "{'file': {'display_name': ' ${ DISPLAY_NAME } '}}" 2 > /dev/null upload_url = $( grep -i "x-goog-upload-url: " " ${ tmp_header_file } " | cut -d " " -f2 | tr -d "\r" ) rm " ${ tmp_header_file } " # Upload the actual bytes. curl " ${ upload_url } " \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -H "Content-Length: ${ NUM_BYTES } " \ -H "X-Goog-Upload-Offset: 0" \ -H "X-Goog-Upload-Command: upload, finalize" \ --data-binary "@ ${ IMAGE_PATH } " 2 > /dev/null > file_info.json file_uri = $( jq -r ".file.uri" file_info.json ) echo file_uri = $file_uri # Now generate content using that file curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -H 'Content-Type: application/json' \ -X POST \ -d '{ "contents": [{ "parts":[ {"file_data":{"mime_type": "' " ${ MIME_TYPE } " '", "file_uri": "' " ${ file_uri } " '"}}, {"text": "Caption this image."}] }] }' 2 > /dev/null > response.json cat response.json echo jq ".candidates[].content.parts[].text" response.json Prompting with multiple images You can provide multiple images in a single prompt by including multiple image Part objects in the contents array. These can be a mix of inline data (local files or URLs) and File API references. Python from google import genai from google.genai import types client = genai . Client () # Upload the first image image1_path = "path/to/image1.jpg" uploaded_file = client . files . upload ( file = image1_path ) # Prepare the second image as inline data image2_path = "path/to/image2.png" with open ( image2_path , 'rb' ) as f : img2_bytes = f . read () # Create the prompt with text and multiple images response = client . models . generate_content ( model = "gemini-2.5-flash" , contents = [ "What is different between these two images?" , uploaded_file , # Use the uploaded file reference types . Part . from_bytes ( data = img2_bytes , mime_type = 'image/png' ) ] ) print ( response . text ) JavaScript import { GoogleGenAI , createUserContent , createPartFromUri , } from "@google/genai" ; import * as fs from "node:fs" ; const ai = new GoogleGenAI ({}); async function main () { // Upload the first image const image1_path = "path/to/image1.jpg" ; const uploadedFile = await ai . files . upload ({ file : image1_path , config : { mimeType : "image/jpeg" }, }); // Prepare the second image as inline data const image2_path = "path/to/image2.png" ; const base64Image2File = fs . readFileSync ( image2_path , { encoding : "base64" , }); // Create the prompt with text and multiple images const response = await ai . models . generateContent ({ model : "gemini-2.5-flash" , contents : createUserContent ([ "What is different between these two images?" , createPartFromUri ( uploadedFile . uri , uploadedFile . mimeType ), { inlineData : { mimeType : "image/png" , data : base64Image2File , }, }, ]), }); console . log ( response . text ); } await main (); Go // Upload the first image image1Path := "path/to/image1.jpg" uploadedFile , _ := client . Files . UploadFromPath ( ctx , image1Path , nil ) // Prepare the second image as inline data image2Path := "path/to/image2.jpeg" imgBytes , _ := os . ReadFile ( image2Path ) parts := [] * genai . Part { genai . NewPartFromText ( "What is different between these two images?" ), genai . NewPartFromBytes ( imgBytes , "image/jpeg" ), genai . NewPartFromURI ( uploadedFile . URI , uploadedFile . MIMEType ), } contents := [] * genai . Content { genai . NewContentFromParts ( parts , genai . RoleUser ), } result , _ := client . Models . GenerateContent ( ctx , "gemini-2.5-flash" , contents , nil , ) fmt . Println ( result . Text ()) REST # Upload the first image IMAGE1_PATH = "path/to/image1.jpg" MIME1_TYPE = $( file -b --mime-type " ${ IMAGE1_PATH } " ) NUM1_BYTES = $( wc -c < " ${ IMAGE1_PATH } " ) DISPLAY_NAME1 = IMAGE1 tmp_header_file1 = upload-header1.tmp curl "https://generativelanguage.googleapis.com/upload/v1beta/files" \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -D upload-header1.tmp \ -H "X-Goog-Upload-Protocol: resumable" \ -H "X-Goog-Upload-Command: start" \ -H "X-Goog-Upload-Header-Content-Length: ${ NUM1_BYTES } " \ -H "X-Goog-Upload-Header-Content-Type: ${ MIME1_TYPE } " \ -H "Content-Type: application/json" \ -d "{'file': {'display_name': ' ${ DISPLAY_NAME1 } '}}" 2 > /dev/null upload_url1 = $( grep -i "x-goog-upload-url: " " ${ tmp_header_file1 } " | cut -d " " -f2 | tr -d "\r" ) rm " ${ tmp_header_file1 } " curl " ${ upload_url1 } " \ -H "Content-Length: ${ NUM1_BYTES } " \ -H "X-Goog-Upload-Offset: 0" \ -H "X-Goog-Upload-Command: upload, finalize" \ --data-binary "@ ${ IMAGE1_PATH } " 2 > /dev/null > file_info1.json file1_uri = $( jq ".file.uri" file_info1.json ) echo file1_uri = $file1_uri # Prepare the second image (inline) IMAGE2_PATH = "path/to/image2.png" MIME2_TYPE = $( file -b --mime-type " ${ IMAGE2_PATH } " ) if [[ " $( base64 --version 2>&1 ) " = * "FreeBSD" * ]] ; then B64FLAGS = "--input" else B64FLAGS = "-w0" fi IMAGE2_BASE64 = $( base64 $B64FLAGS $IMAGE2_PATH ) # Now generate content using both images curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \ -H "x-goog-api-key: $GEMINI_API_KEY " \ -H 'Content-Type: application/json' \ -X POST \ -d '{ "contents": [{ "parts":[ {"text": "What is different between these two images?"}, {"file_data":{"mime_type": "' " ${ MIME1_TYPE } " '", "file_uri": ' $file1_uri '}}, { "inline_data": { "mime_type":"' " ${ MIME2_TYPE } " '", "data": "' " $IMAGE2_BASE64 " '" } } ] }] }' 2 > /dev/null > response.json cat response.json echo jq ".candidates[].content.parts[].text" response.json Object detection From Gemini 2.0 onwards, models are further trained to detect objects in an image and get their bounding box coordinates. The coordinates, relative to image dimensions, scale to [0, 1000]. You need to descale these coordinates based on your original image size. Python from google import genai from google.genai import types from PIL import Image import json client = genai . Client () prompt = "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000." image = Image . open ( "/path/to/image.png" ) config = types . GenerateContentConfig ( response_mime_type = "application/json" ) response = client . models . generate_content ( model = "gemini-2.5-flash" , contents = [ image , prompt ], config = config ) width , height = image . size bounding_boxes = json . loads ( response . text ) converted_bounding_boxes = [] for bounding_box in bounding_boxes : abs_y1 = int ( bounding_box [ "box_2d" ][ 0 ] / 1000 * height ) abs_x1 = int ( bounding_box [ "box_2d" ][ 1 ] / 1000 * width ) abs_y2 = int ( bounding_box [ "box_2d" ][ 2 ] / 1000 * height ) abs_x2 = int ( bounding_box [ "box_2d" ][ 3 ] / 1000 * width ) converted_bounding_boxes . append ([ abs_x1 , abs_y1 , abs_x2 , abs_y2 ]) print ( "Image size: " , width , height ) print ( "Bounding boxes:" , converted_bounding_boxes ) Note: The model also supports generating bounding boxes based on custom instructions, such as: "Show bounding boxes of all green objects in this image". It also support custom labels like "label the items with the allergens they can contain". For more examples, check following notebooks in the Gemini Cookbook : 2D spatial understanding notebook Experimental 3D pointing notebook Segmentation Starting with Gemini 2.5, models not only detect items but also segment them and provide their contour masks. The model predicts a JSON list, where each item represents a segmentation mask. Each item has a bounding box (" box_2d ") in the format [y0, x0, y1, x1] with normalized coordinates between 0 and 1000, a label (" label ") that identifies the object, and finally the segmentation mask inside the bounding box, as base64 encoded png that is a probability map with values between 0 and 255. The mask needs to be resized to match the bounding box dimensions, then binarized at your confidence threshold (127 for the midpoint). Note: For better results, disable thinking by setting the thinking budget to 0. See code sample below for an example. Python from google import genai from google.genai import types from PIL import Image , ImageDraw import io import base64 import json import numpy as np import os client = genai . Client () def parse_json ( json_output : str ): # Parsing out the markdown fencing lines = json_output . splitlines () for i , line in enumerate ( lines ): if line == "```json" : json_output = " \n " . join ( lines [ i + 1 :]) # Remove everything before "```json" output = json_output . split ( "```" )[ 0 ] # Remove everything after the closing "```" break # Exit the loop once "```json" is found return json_output def extract_segmentation_masks ( image_path : str , output_dir : str = "segmentation_outputs" ): # Load and resize image im = Image . open ( image_path ) im . thumbnail ([ 1024 , 1024 ], Image . Resampling . LANCZOS ) prompt = """ Give the segmentation masks for the wooden and glass items. Output a JSON list of segmentation masks where each entry contains the 2D bounding box in the key "box_2d", the segmentation mask in key "mask", and the text label in the key "label". Use descriptive labels. """ config = types . GenerateContentConfig ( thinking_config = types . ThinkingConfig ( thinking_budget = 0 ) # set thinking_budget to 0 for better results in object detection ) response = client . models . generate_content ( model = "gemini-2.5-flash" , contents = [ prompt , im ], # Pillow images can be directly passed as inputs (which will be converted by the SDK) config = config ) # Parse JSON response items = json . loads ( parse_json ( response . text )) # Create output directory os . makedirs ( output_dir , exist_ok = True ) # Process each mask for i , item in enumerate ( items ): # Get bounding box coordinates box = item [ "box_2d" ] y0 = int ( box [ 0 ] / 1000 * im . size [ 1 ]) x0 = int ( box [ 1 ] / 1000 * im . size [ 0 ]) y1 = int ( box [ 2 ] / 1000 * im . size [ 1 ]) x1 = int ( box [ 3 ] / 1000 * im . size [ 0 ]) # Skip invalid boxes if y0 > = y1 or x0 > = x1 : continue # Process mask png_str = item [ "mask" ] if not png_str . startswith ( "data:image/png;base64," ): continue # Remove prefix png_str = png_str . removeprefix ( "data:image/png;base64," ) mask_data = base64 . b64decode ( png_str ) mask = Image . open ( io . BytesIO ( mask_data )) # Resize mask to match bounding box mask = mask . resize (( x1 - x0 , y1 - y0 ), Image . Resampling . BILINEAR ) # Convert mask to numpy array for processing mask_array = np . array ( mask ) # Create overlay for this mask overlay = Image . new ( 'RGBA' , im . size , ( 0 , 0 , 0 , 0 )) overlay_draw = ImageDraw . Draw ( overlay ) # Create overlay for the mask color = ( 255 , 255 , 255 , 200 ) for y in range ( y0 , y1 ): for x in range ( x0 , x1 ): if mask_array [ y - y0 , x - x0 ] > 128 : # Threshold for mask overlay_draw . point (( x , y ), fill = color ) # Save individual mask and its overlay mask_filename = f " { item [ 'label' ] } _ { i } _mask.png" overlay_filename = f " { item [ 'label' ] } _ { i } _overlay.png" mask . save ( os . path . join ( output_dir , mask_filename )) # Create and save overlay composite = Image . alpha_composite ( im . convert ( 'RGBA' ), overlay ) composite . save ( os . path . join ( output_dir , overlay_filename )) print ( f "Saved mask and overlay for { item [ 'label' ] } to { output_dir } " ) # Example usage if __name__ == "__main__" : extract_segmentation_masks ( "path/to/image.png" ) Check the segmentation example in the cookbook guide for a more detailed example. An example segmentation output with objects and segmentation masks Supported image formats Gemini supports the following image format MIME types: PNG - image/png JPEG - image/jpeg WEBP - image/webp HEIC - image/heic HEIF - image/heif To learn about other file input methods, see the File input methods guide. Capabilities All Gemini model versions are multimodal and can be utilized in a wide range of image processing and computer vision tasks including but not limited to image captioning, visual question and answering, image classification, object detection and segmentation. Gemini can reduce the need to use specialized ML models depending on your quality and performance requirements. Some later model versions are specifically trained improve accuracy of specialized tasks in addition to generic capabilities: Gemini 2.0 models are further trained to support enhanced object detection . Gemini 2.5 models are further trained to support enhanced segmentation in addition to object detection . Limitations and key technical information File limit Gemini 2.5 Pro/Flash, 2.0 Flash, 1.5 Pro, and 1.5 Flash support a maximum of 3,600 image files per request. Token calculation Gemini 1.5 Flash and Gemini 1.5 Pro : 258 tokens if both dimensions <= 384 pixels. Larger images are tiled (min tile 256px, max 768px, resized to 768x768), with each tile costing 258 tokens. Gemini 2.0 Flash and Gemini 2.5 Flash/Pro : 258 tokens if both dimensions <= 384 pixels. Larger images are tiled into 768x768 pixel tiles, each costing 258 tokens. A rough formula for calculating the number of tiles is as follows: Calculate the crop unit size which is roughly: floor(min(width, height) / 1.5). Divide each dimension by the crop unit size and multiply together to get the number of tiles. For example, for an image of dimensions 960x540 would have a crop unit size of 360. Divide each dimension by 360 and the number of tile is 3 * 2 = 6. Media resolution Gemini 3 introduces granular control over multimodal vision processing with the media_resolution parameter. The media_resolution parameter determines the maximum number of tokens allocated per input image or video frame. Higher resolutions improve the model's ability to read fine text or identify small details, but increase token usage and latency. For more details about the parameter and how it can impact token calculations, see the media resolution guide. Tips and best practices Verify that images are correctly rotated. Use clear, non-blurry images. When using a single image with text, place the text prompt after the image part in the contents array. What's next This guide shows you how to upload image files and generate text outputs from image inputs. To learn more, see the following resources: Files API : Learn more about uploading and managing files for use with Gemini. System instructions : System instructions let you steer the behavior of the model based on your specific needs and use cases. File prompting strategies : The Gemini API supports prompting with text, image, audio, and video data, also known as multimodal prompting. Safety guidance : Sometimes generative AI models produce unexpected outputs, such as outputs that are inaccurate, biased, or offensive. Post-processing and human evaluation are essential to limit the risk of harm from such outputs. Send feedback Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates. Last updated 2026-01-12 UTC. Need to tell us more? [[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-01-12 UTC."],[],[]] Terms Privacy Manage cookies English Deutsch Español – América Latina Français Indonesia Italiano Polski Português – Brasil Shqip Tiếng Việt Türkçe Русский עברית العربيّة فارسی हिंदी বাংলা ภาษาไทย 中文 – 简体 中文 – 繁體 日本語 한국어 | 2026-01-13T09:29:16 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Ffreshworks-inc-freshdesk%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:16 |
https://scholar.google.com/citations?user=tq-LVzIAAAAJ&hl=ko&oe=ASCII | Zhipeng Cai - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 21340 12979 h-index 73 51 i10-index 283 197 0 3100 1550 775 2325 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 69 118 289 323 424 750 1045 1623 1534 1829 2441 2075 2341 2953 3025 106 공개 액세스 모두 보기 모두 보기 자료 172개 자료 129개 공개 비공개 재정 지원 요구사항 기준 공동 저자 모두 보기 Yingshu Li Professor, Georgia State University gsu.edu의 이메일 확인됨 Hong Gao Zhejiang Normal University zjnu.edu.cn의 이메일 확인됨 Wei (Lisa) Li Assistant Professor, Department of Computer Science, Georgia State University gsu.edu의 이메일 확인됨 Zaobo He Jinan University (暨南大学) jnu.edu.cn의 이메일 확인됨 xu zheng University of Electronic Science and Technology of China uestc.edu.cn의 이메일 확인됨 Guohui Lin Computing Science, University of Alberta ualberta.ca의 이메일 확인됨 Quan Chen Guangdong University of Technology gdut.edu.cn의 이메일 확인됨 Tuo Shi Aalto University aalto.fi의 이메일 확인됨 Jiguo Yu，Professor, FIEEE, FAAIA University of Electronic Science and Technology of China uestc.edu.cn의 이메일 확인됨 Yan Huang Kennesaw State University kennesaw.edu의 이메일 확인됨 Zuobin Xiong Assistant Professor, Dept. of Computer Science, University of Nevada, Las Vegas unlv.edu의 이메일 확인됨 Dongxiao Yu Professor of Computer Science, Shandong University sdu.edu.cn의 이메일 확인됨 Yi Pan Shenzhen University of Advanced Technology, China cs.gsu.edu의 이메일 확인됨 Xiu-Feng Wan or Xiufeng Wan University of Missouri-Columbia missouri.edu의 이메일 확인됨 Meng Han Intelligence Fusion Research Center （IFRC） zju.edu.cn의 이메일 확인됨 Raheem Beyah Dean and Southern Company Chair, Georgia Tech College of Engineering ece.gatech.edu의 이메일 확인됨 Daniel Takabi Professor and Director of School of Cybersecurity, Old Dominion University odu.edu의 이메일 확인됨 Dongjing Miao Harbin Institute of Technology hit.edu.cn의 이메일 확인됨 Randy Goebel Professor of Computing Science, University of Alberta ualberta.ca의 이메일 확인됨 Qi Luo Hong Kong University of Science and Technology ust.hk의 이메일 확인됨 모두 보기 팔로우 Zhipeng Cai Professor, IEEE Fellow, DMACM, Georgia State University cs.gsu.edu의 이메일 확인됨 - 홈페이지 Internet of Things Privacy Algorithm Big Data Networking 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Artificial intelligence: A powerful paradigm for scientific research Y Xu, X Liu, X Cao, C Huang, E Liu, S Qian, X Liu, Y Wu, F Dong, CW Qiu, ... The Innovation 2 (4) , 2021 2042 2021 Collective data-sanitization for preventing sensitive information inference attacks in social networks Z Cai, Z He, X Guan, Y Li IEEE Transactions on Dependable and Secure Computing 15 (4), 577-590 , 2016 666 2016 A private and efficient mechanism for data uploading in smart cyber-physical systems Z Cai, X Zheng IEEE Transactions on Network Science and Engineering 7 (2), 766-775 , 2018 626 2018 Privacy-preserved data sharing towards multiple parties in industrial IoTs X Zheng, Z Cai IEEE journal on selected areas in communications 38 (5), 968-979 , 2020 520 2020 Generative adversarial networks: A survey toward private and secure applications Z Cai, Z Xiong, H Xu, P Wang, W Li, Y Pan ACM Computing Surveys (CSUR) 54 (6), 1-38 , 2021 462 2021 Trading private range counting over big IoT data Z Cai, Z He 2019 IEEE 39th International Conference on Distributed Computing Systems�… , 2019 383 2019 Cost-efficient strategies for restraining rumor spreading in mobile social networks Z He, Z Cai, J Yu, X Wang, Y Sun, Y Li IEEE Transactions on Vehicular Technology 66 (3), 2789-2800 , 2016 327 2016 Security and privacy in metaverse: A comprehensive survey Y Huang, YJ Li, Z Cai Big Data Mining and Analytics 6 (2), 234-247 , 2023 320 2023 Deep learning based inference of private information using embedded sensors in smart devices Y Liang, Z Cai, J Yu, Q Han, Y Li IEEE Network 32 (4), 8-14 , 2018 282 2018 Privacy threat and defense for federated learning with non-iid data in AIoT Z Xiong, Z Cai, D Takabi, W Li IEEE Transactions on Industrial Informatics 18 (2), 1310-1321 , 2021 257 2021 A stable gene selection in microarray data analysis K Yang, Z Cai, J Li, G Lin BMC bioinformatics 7 (1), 228 , 2006 249 2006 A differential-private framework for urban traffic flows estimation via taxi companies Z Cai, X Zheng, J Yu IEEE Transactions on Industrial Informatics 15 (12), 6492-6499 , 2019 246 2019 Data linkage in smart internet of things systems: a consideration from a privacy perspective X Zheng, Z Cai, Y Li IEEE Communications Magazine 56 (9), 55-61 , 2018 240 2018 An incentive mechanism with privacy protection in mobile crowdsourcing systems Y Wang, Z Cai, G Yin, Y Gao, X Tong, G Wu Computer Networks 102, 157-171 , 2016 232 2016 Avian-origin H3N2 canine influenza A viruses in Southern China S Li, Z Shi, P Jiao, G Zhang, Z Zhong, W Tian, LP Long, Z Cai, X Zhu, ... Infection, Genetics and Evolution 10 (8), 1286-1288 , 2010 231 2010 Collaborative city digital twin for the COVID-19 pandemic: A federated learning solution J Pang, Y Huang, Z Xie, J Li, Z Cai Tsinghua science and technology 26 (5), 759-771 , 2021 229 2021 zkCrowd: a hybrid blockchain-based crowdsourcing platform S Zhu, Z Cai, H Hu, Y Li, W Li IEEE Transactions on Industrial Informatics 16 (6), 4196-4205 , 2019 229 2019 Realizing the heterogeneity: A self-organized federated learning framework for IoT J Pang, Y Huang, Z Xie, Q Han, Z Cai IEEE Internet of Things Journal 8 (5), 3088-3098 , 2020 216 2020 Using crowdsourced data in location-based social networks to explore influence maximization JLZ Cai, M Yan, Y Li IEEE INFOCOM 2016-The 35th Annual IEEE International Conference on Computer�… , 2016 205 2016 Latent-data privacy preserving with customized data utility for social network data Z He, Z Cai, J Yu IEEE Transactions on Vehicular Technology 67 (1), 665-673 , 2017 204 2017 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:16 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.