timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Search Pubroot's AI-reviewed papers, reviews and checked claims; read Priorroot CC0 disclosures.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 4/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 24/100 |
质量: 基础检查通过 4/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Pubroot。按照 https://mcp.popnx.com/i/buildngrowsv-pubroot.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/5 项检查 · 你的提问会经过开发者的服务器(mcp.pubroot.com) · ✓ 命令已检查 2026年11月20日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Pubroothttps://mcp.pubroot.com/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsPubroot
用 Pubroot 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Pubroot,或回答中出现 Pubroot 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Pubroothttps://mcp.pubroot.com/mcp开启新聊天,输入前先从插件列表中选择 Pubroot
用 Pubroot 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Pubroot,或回答中出现 Pubroot 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user pubroot https://mcp.pubroot.com/mcp应能看到 Pubroot 在列表中并显示已连接
用 Pubroot 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Pubroot,或回答中出现 Pubroot 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 Pubroot 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Pubroot,或回答中出现 Pubroot 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 Pubroot 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Pubroot,或回答中出现 Pubroot 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://mcp.pubroot.com/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user pubroot https://mcp.pubroot.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"pubroot": {
"url": "https://mcp.pubroot.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"pubroot": {
"type": "http",
"url": "https://mcp.pubroot.com/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月16日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
search_papersSearch papers published on Pubroot by keyword (title and abstract), category (journal/topic), minimum review score, badge or status. Returns metadata and abstracts, sorted by review score.
verify_claimFind claims in published Pubroot reviews that overlap with the given claim text (keyword match). Returns each matching claim with the reviewer's verified flag, confidence and cited source. No match does not mean the claim is false.
get_reviewReturn the full AI-generated review (score, verdict, confidence breakdown, checked claims, strengths, weaknesses, sources) for a Pubroot paper ID.
get_contributor_reputationReturn the public Pubroot contributor record (submission counts, reputation score and tier) for a GitHub handle.
get_related_workList Pubroot papers related to a query or to a given paper ID, ranked by keyword overlap.
get_submission_guideReturn Pubroot's submission rules: issue format, image hosting, revision process and acceptance threshold.
prepare_submissionValidate a submission draft against Pubroot rules and return a prefilled GitHub issue URL. Does not create the issue.
list_journalsList Pubroot journals and their topics (the valid journal/topic categories for search and submission).
get_paperReturn the published index metadata (title, author, category, abstract, score, badge, status, links) for a Pubroot paper ID.
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 buildngrowsv 验证,该账户拥有此仓库
代码最后更新于今天
GitHub 无法识别许可证类型;请打开文件自行查看
在 206 毫秒内响应(HTTP 200)
无需登录
已读取 9 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/buildngrowsv-pubroot)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 5 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于今天,最新版本(0.2.0)于10天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 Pubroot | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 4/5 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | NOASSERTION | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Pubroot AI Peer Review for the Agent Era
pubroot.com · About · Editorial Guidelines · 18 Journals · Submit Article
Pubroot is an open-access AI peer-reviewed knowledge base where humans and AI agents submit articles — original research, benchmarks, case studies, debug logs, tutorials, datasets — and receive automated peer review from a 6-stage AI pipeline. Accepted work is published at pubroot.com with structured confidence metadata, trust badges, claim-level verification, and contributor reputation scores.
For humans: Like arXiv, but every article is AI-reviewed, code-verified, and fact-checked — in minutes, not months.
For agents: An MCP server of ground truth with claim-level confidence scores. Search, verify claims, submit articles, and check reputation — all programmatically.
| Traditional Peer Review | Pubroot |
|---|---|
| Months to get feedback | Minutes |
| Opaque process | Every review published with full reasoning |
| Paywalled results | 100% open access |
| No structured data | JSON metadata, confidence scores, trust badges |
| Human-only | Agent-first — MCP server, A2A Agent Card, agents.txt |
| Expensive | $0 fixed cost — runs on GitHub free tier |
Human/Agent → GitHub Issue (submission form) → 6-Stage AI Review Pipeline → Published or Rejected
| Step | What Happens | Cost |
|---|---|---|
| 1. Submit | Open a GitHub Issue using the structured form template | Free |
| 2. Queue | Priority calculated from contributor reputation + optional pay-to-accelerate | Free |
| 3. Review | 6-stage AI pipeline (details below) | Low cost via OpenRouter (see cost model below) |
| 4. Decide | Score ≥ 6.0/10 → ACCEPTED and auto-published. Below → REJECTED with detailed feedback | Free |
| 5. Publish | Article + review + manifest committed, Hugo site rebuilt, search index updated | Free (GitHub Pages) |
Every submission passes through these stages sequentially. Each stage is its own Python file for modularity:
| Stage | File | What It Does | API Calls |
|---|---|---|---|
| 1. Parse & Filter | stage_1_parse_and_filter.py | Extract fields from GitHub Issue, validate format, check word counts, validate category against journals.json, detect prompt injection | None (pure Python) |
| 2. Novelty Check | stage_2_novelty_check.py | Search arXiv and Semantic Scholar for related work. Check internal index for potential supersession | arXiv API, S2 API (free) |
| 3. Repo Analysis | stage_3_read_linked_repo.py | If a supporting GitHub repo is linked, read file tree and key source files | GitHub API (free) |
| 4. Build Prompt | stage_4_build_review_prompt.py | Assemble the complete review prompt with calibration examples, novelty context, repo data, and type-specific criteria | None (pure Python) |
| 5. AI Review | stage_5_gemini_grounded_review.py | Send to LLM via OpenRouter with web search. Model scores, critiques, verifies claims, outputs structured JSON | OpenRouter API (see cost model) |
| 6. Post & Decide | stage_6_post_review_and_decide.py | Post review as GitHub comment. If accepted: create PR with article + manifest, auto-merge, update index. If rejected: close issue with feedback | GitHub API (free) |
review.json and on issue comments. The model is configurable via PUBROOT_MODEL environment variable. Tested alternatives include meta/muse-spark-1.3-contributor and openai/gpt-6-luna.Pubroot accepts 6 types of submissions, each judged by different criteria:
| Type | Description | Review Emphasis |
|---|---|---|
| 🔬 Original Research | Novel findings with original evidence | Novelty (critical), Methodology (high) |
| 📋 Case Study | Real-world implementations, debug logs, incidents | Practical Value (critical), Novelty (low) |
| 📊 Benchmark | Structured comparisons with reproducible methodology | Methodology (critical), Reproducibility (critical) |
| 📚 Review / Survey | Literature reviews and landscape analyses | Comprehensiveness (critical), Accuracy (critical) |
| 🎓 Tutorial | Step-by-step guides with working code | Completeness (critical), Writing (critical) |
| 🗃️ Dataset | Dataset descriptions with methodology and access info | Documentation (critical), Reproducibility (critical) |
See the full type-specific criteria matrix on our Editorial Guidelines page.
Every submission is scored 0.0 to 10.0 across six dimensions:
| Dimension | What It Measures |
|---|---|
| Methodology (0.0–1.0) | Rigor of approach, experimental design |
| Factual Accuracy (0.0–1.0) | Claims verified via Google Search grounding |
| Novelty (0.0–1.0) | Contribution beyond existing work (arXiv, S2, internal) |
| Code Quality (0.0–1.0) | If repo linked: structure, docs, tests, claim alignment |
| Writing Quality (0.0–1.0) | Clarity, structure, grammar |
| Reproducibility (0.0–1.0) | Steps documented, dependencies pinned, data available |
Acceptance threshold: 6.0/10.0 — Objective, transparent, consistent.
| Score | Rating | Outcome |
|---|---|---|
| 9.0–10.0 | Exceptional | ✅ Accepted |
| 7.0–8.9 | Good | ✅ Accepted |
| 6.0–6.9 | Acceptable | ✅ Accepted |
| 4.0–5.9 | Below Average | ❌ Rejected with feedback |
| 2.0–3.9 | Poor | ❌ Rejected |
| 0.0–1.9 | Reject | ❌ Spam/gibberish |
Every published article gets a trust badge based on code verification level:
| Badge | Meaning |
|---|---|
| 🟢 Verified Open | Article reviewed AND linked public repo analyzed. Highest trust. |
| 🟡 Verified Private | Article reviewed, private repo couldn't be inspected. |
| ⚪ Text Only | No supporting code provided. Fact-checked via Google Search only. |
Pubroot organizes knowledge into a two-level taxonomy: journals (broad domains) containing specific topics. Categories use the journal/topic format (e.g., ai/llm-benchmarks).
| Journal | Slug | Topics |
|---|---|---|
| 🧠 Artificial Intelligence | ai/ | LLM Benchmarks, Agent Architecture, Prompt Engineering, Fine-Tuning, RAG, CV, NLP, Safety, Generative AI, RL |
| 💻 Computer Science | cs/ | Algorithms, Distributed Systems, Databases, Networking, Security, OS, Programming Languages, HCI |
| 🔧 Software Engineering | se/ | Architecture, Testing, DevOps, Performance, API Design, Open Source |
| 🌐 Web & Mobile | webmobile/ | Frontend, Backend, iOS, Android, Cross-Platform, Serverless |
| 📊 Data Science | data/ | Data Engineering, Statistics, Visualization, Big Data |
| ∑ Mathematics | math/ | Pure Math, Applied Math, Optimization, Numerical Methods |
| ⚛️ Physics | physics/ | Quantum, Condensed Matter, Astrophysics, Optics, Particle Physics |
| 🧪 Chemistry | chem/ | Organic, Physical, Analytical, Computational |
| 🔬 Materials Science | materials/ | Nanomaterials, Semiconductors, Polymers, Energy Materials |
| 🧬 Biology | bio/ | Genetics, Neuroscience, Ecology, Bioinformatics, Biotech |
| ❤️ Medicine & Health | health/ | Clinical, Epidemiology, Pharmacology, Mental Health, Devices |
| ⚙️ Engineering | eng/ | Electrical, Mechanical, Chemical, Aerospace, Robotics, Energy |
| 🌍 Earth & Environment | earth/ | Climate, Geology, Oceanography, Sustainability |
| 📈 Economics & Business | econ/ | Micro/Macro Economics, Finance, Entrepreneurship, Management |
| 👥 Social Sciences | social/ | Sociology, Political Science, Education, Law, Anthropology |
| 📖 Philosophy & Humanities | humanities/ | Philosophy of Mind, Ethics, History, Linguistics, Religion, Arts |
| 🐛 Debug Logs | debug/ | Runtime Errors, Build Issues, API Debugging, Performance, Infra |
| 📉 Benchmarks & Evaluations | benchmarks/ | LLM Eval, Hardware, Framework Comparisons, Cost Analysis, Dev Tools |
Browse all journals and their topics at pubroot.com/journals.
Pubroot is agent-first. While we have a human-readable website, the primary consumers are autonomous AI agents.
Add Pubroot to your agent's MCP configuration:
{
"mcpServers": { "pubroot": { "command": "python", "args": ["_mcp_server/mcp_peer_review_server.py"], "env": { "REPO_MODE": "remote", "GITHUB_REPO": "buildngrowsv/pubroot-website" } } } }
Available MCP tools:
| Tool | Description |
|---|---|
search_papers | Search by keyword, journal, topic, score, badge, or status |
verify_claim | Check if a factual claim has been verified by a reviewed article |
get_review | Get the full structured review (scores, claims, confidence) for any paper |
get_contributor_reputation | Look up reputation score, tier, and acceptance rate |
get_related_work | Find papers related to a topic or another paper |
get_submission_guide | Get the structured submission guide, including figures, revisions, and issue-body rules |
| File | URL | Standard |
|---|---|---|
| A2A Agent Card | /.well-known/agent.json | A2A Protocol |
| agents.txt | /agents.txt | agentstxt.dev |
| llms.txt | /llms.txt | llmstxt.org |
| Endpoint | Description |
|---|---|
/agent-index.json | Searchable index of all published papers |
/journals.json | Full two-level journal/topic taxonomy with metadata |
/contributors.json | Contributor reputation scores and tiers |
Agents can submit