Noether Physics

io.github.Ranshiv由 GitHub 账号 Ranshiv 发布v0.1.2更新于 Oct 24, 2026

Physics assistant: checked equations, live simulations, claims verified against arXiv papers

概览

AI 生成的概览

物理研究助手:讲解概念、运行模拟、检查方程,并对照真实 arXiv 论文核验引用。

可以做什么
  • 用类比讲解物理概念,给出量纲检查过的方程和重新计算的例题
  • 运行六种物理模拟(单摆、阻尼/受迫振子、带阻力抛体、Rabi、退相干、Jaynes-Cummings),并报告漂移与解析解对比
  • 检查方程的量纲一致性,未声明的符号返回 unknown 而非猜测
  • 导入 arXiv 的 LaTeX 源文件,列出其中的方程并在论文库中检索
  • 审计草稿的参考文献,在 arXiv、Crossref、OpenAlex 和 INSPIRE 上解析每条引用
适用场景
适合需要可核验依据的物理问答场景:讲解概念、快速跑模拟、检查方程,或在投稿前发现草稿中不存在或无法解析的参考文献。
运行要求
以 PyPI 包 noether-physics 通过 stdio 在本地运行,需安装 mcp 附加组件;需要 Python 3.12+ 以及访问 arXiv 和引用索引的网络。量子模拟需安装 quantum 附加组件(QuTiP)。未声明任何账号、API 密钥或环境变量。
安装前请注意
验证环节只确认引文真实存在,不确认其支持该论断,因此应自行阅读所引原文。引用解析器仅用 8 条伪造文献测试过,覆盖范围也小(58 篇论文、8 个概念)。审计在引用无法解析时以非零状态退出,可能中断 pre-commit 钩子。arXiv 禁止批量抓取,该工具逐篇抓取并间隔 3 秒。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Noether Physics,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

NOETHER

A physics research assistant that shows its work.

Explains physics concepts with everyday analogies, dimension-checked equations, worked examples it recomputes, and simulations it actually runs. Answers questions from real arXiv papers with every sentence anchored to a verbatim span. Audits your own draft's bibliography for references that don't exist.

bash
pip install noether-physicsnoether explain decoherence

On 0.1.0 or 0.1.1? Upgrade. Those releases confirm fabricated references — the specific failure this tool exists to prevent. See CHANGELOG.md.


Read this before you trust it

This is a research-integrity tool, so its limits matter more than its features.

The verification gate checks that a quote is real. It does not check that the quote supports the claim. A claim can contradict its own citation and still pass. Demonstrated during development: a claim asserting "the experiment detected a nonzero neutron EDM at five sigma" was accepted while citing a passage reporting d_n = 0.0 ± 1.1 × 10⁻²⁶ e·cm — a null result. The quote was genuine, so the gate let it through. Closing that gap needs entailment checking, which needs a language model, and keeping the model outside the verifier is what makes the other guarantees meaningful. So every answer this tool emits ends by saying so, and you should read the quotes.

The reference resolver is now measured in both directions. It resolves 86.5% of real references and was fooled by 0 of 8 deliberately fabricated ones. That second number did not exist until a labelled benchmark was built for it — and the first run of that benchmark caught the resolver confirming 80% of fabrications, some at 0.95 confidence. Three defects were found and fixed. Eight fabrications is still a small sample: 0% means "fooled by none of eight", not "cannot be fooled".

It is small. 58 papers in the test corpus, 8 concepts in the explanation library, quantum coverage limited to two-level systems and one cavity mode. No PDF fallback, so roughly 9% of quant-ph papers (measured: 5 of 55) cannot be ingested at all.

docs/DEFERRED.md is the full account — every gap, with the measurement behind it. It is the honest document; this README is the summary.


Why it exists

2026 audits found a 17% phantom-citation rate in AI-assisted survey papers — references resolving to no digital object — and roughly 146,900 AI-generated fake citations across 2.5M papers in 2025. arXiv now bans authors who submit hallucinated references.

Physics has a structural advantage nobody exploits: arXiv distributes the actual LaTeX source. Equations arrive with their \labels, citations with their \cite keys, sections with their real structure — read, not guessed. Tools in other fields OCR PDFs because their domains have no source. Physics does.

What it does

Explains. Curated prose, not generated — then machine-checked. Every equation is parsed and dimension-checked; every worked example is recomputed and compared against its stored answer, so a typo in the library fails CI rather than teaching you a wrong number.

bash
noether explain decoherence          # analogy, maths, worked example, live simulationnoether concepts                     # what the library covers

Simulates. Six models — pendulum, damped/driven oscillator, projectile with drag (SciPy); Rabi, decoherence, Jaynes-Cummings (QuTiP). Every run halves the step size and reports the drift, and where a closed form exists the numerics are compared against it automatically.

bash
noether simulate rabi --params "detuning=6.28" --blochnoether models

Checks equations. Undeclared symbols return unknown, never a guess — h is Planck's constant or a height, T a period or a temperature. unknown is not a pass.

bash
noether eq 'T = 2 \pi \sqrt{\frac{L}{g}}' --units 'T=second,L=meter,g=meter/second**2' --vary 'L=0.1..2' --at 'g=9.81'

Reads papers. Ingests LaTeX source, so "equation 14" means the equation the authors numbered 14.

bash
noether ingest 2001.11966noether equations arXiv:2001.11966noether find "vacuum Rabi oscillations"

Audits your draft. Resolves every \bibitem against arXiv, Crossref, OpenAlex and INSPIRE. Exits non-zero on unresolvable references or cite keys with no bibliography entry, so it works as a pre-commit hook.

bash
noether audit path/to/your-paper.tex

Measured results

Run noether bench status yourself. As of the last run:

gateresultthresholdverdict
equations100% (31/31)90%pass
retrieval83.3% (10/12) at top-3 of 58 papers80%pass
citations86.5% (32/37)85%pass
resolver0% false positives (0/8 fabrications)≤10%pass

Read these with their scope attached. "Right paper in the top 3" over 58 papers is a real task; over 8 it was nearly free, and an earlier run reported a meaningless 100% because top_k exceeded the corpus size. The citation threshold is 85% rather than 100% because books, theses and pre-digital articles are genuinely not in any index — the residual failures on the nEDM letter are a 1954 Danish journal, a 1955 Pauli chapter and a 1982 Oxford book.

Use it from Claude

bash
pip install "noether-physics[mcp]"claude mcp add --scope user noether -- python -m noether.mcp_server

14 tools. Claude reasons and writes; NOETHER retrieves, checks and records. There is deliberately no write_answer tool — the component that can hallucinate is not the component that decides what ships.

Install

bash
pip install noether-physics              # corepip install "noether-physics[quantum]"   # + QuTiP simulationspip install "noether-physics[mcp]"       # + MCP server

Python 3.12+. From source: uv venv && uv pip install -e ".[dev,quantum,mcp]", then uv run pytest (288 tests, no network — cassettes default to replay and a miss is an error, not a live fallback).

Terms

arXiv forbids bulk crawling. This fetches one paper at a time behind a 3-second interval and caches permanently, so a given paper is downloaded exactly once. Every source, its rate limit and its terms are declared in research/sources/source_registry.yaml; a source not in that file is not called.

No AI-generated imagery. Every figure is extracted from a real paper or rendered deterministically from code and data, and is tagged with which.

Licence

MIT — see LICENSE. Release history: CHANGELOG.md.

The name honours Emmy Noether. The PyPI distribution is noether-physics because noether belongs to an unrelated physical-units library; the command is noether either way.

来源:README.md,提交 35faf21

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.2最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分