
Security News
arXiv Is Rate Limiting Authors Following a Flood of AI Slop Submissions
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.
lingshu-solver
Advanced tools
Lingshu Solver — deterministic (non-LLM) MCP tool for solving systems of real equations, up to 6 variables: interval arithmetic + affine arithmetic + constructive Krawczyk certification, zero dependencies, offline, no data upload, unproven-completeness ho
Category: Certified Real-Root Computation
A deterministic solver for systems of real equations. The same problem always produces the same answer — no language model, no randomness, no hallucination. Every solution it reports is Krawczyk-certified (
certified: true), reproducible, checkable by substitution, and usable as an audit trail.
Two audiences: people who just want an answer (open the web page, no install), and AI agents (a standard MCP tool, one line to connect).
🔬 Live demo against the production endpoint:
https://hclj-1409755229.cos.ap-guangzhou.myqcloud.com/lingshu-solver/demo.html — call the real MCP
endpoint right from the browser and watch poly_roots return certified real roots and verify judge a
candidate value. Thirty seconds is enough to see why "an LLM will mis-compute this, Lingshu can certify it".
| Yes | a deterministic (non-LLM) numerical engine for systems of real equations; algebraic equations and common transcendentals (sin/cos/tan/log/exp/sqrt/abs) all work |
| No | a symbolic CAS (no analytic derivation), an ODE solver, an integer-programming solver, and it does not claim guaranteed completeness |
① Web (zero install, permanently free)
Type equations into the box (for example x^2 + y^2 = 25 and x + y = 7) and press solve. Everything is
computed inside your browser; the equations never leave your device.
② AI agent (MCP — pick either form)
// local stdio — permanently free, unlimited, offline. Recommended.
{ "mcpServers": { "lingshu-solver": { "command": "npx", "args": ["-y", "lingshu-solver"] } } }
// hosted endpoint — no install, always on, reachable over the public internet
{ "mcpServers": { "lingshu-solver": { "type": "http", "url": "https://hongchenlingjing.com/mcp" } } }
It also works if you never pay: the hosted endpoint runs on an honor system — pass
"honorPaid": truein thesolvearguments and the call is released for free (no verification, no balance deduction). Thenpxlocal version and the web version are permanently free. If you do want to support it, see the payment page — a corporate account, self-service crediting, effective immediately, no human approval anywhere in the loop.
③ Developer
git clone https://github.com/genesis-plan/lingshu-solver.git
cd lingshu-solver
node mcp-server.js # start the local MCP (stdio) server
node test/regression.js # standing regression suite
| Dimension | What it means |
|---|---|
| Verified solutions | every reported solution is Krawczyk-certified (tier=proven); error is within the certified radius; mathematically faithful |
| Completeness | best effort at finding all solutions; when exhaustiveness could not be proven within budget it says so explicitly with truncated=true — it never claims completeness it did not prove |
truncated semantics | only means "the global branch search did not finish inside the budget"; it does not mean solutions were missed. In most cases every real solution was found |
| Variables | ≤ 6 |
| Equations | 1–64 (server-side guard), and the count must be ≥ the variable count |
| Search range | default ±1e6 per variable; supply domain explicitly for fast-growing functions (exp/sinh) |
| Output precision | fixed at 6 decimal places (there is no precision switch) |
| Determinism | no random branching; identical input always yields identical output, so caching is safe |
| Data | web version sends nothing upward; local version runs offline; the hosted endpoint does not persist equation contents |
| Dependencies | zero third-party dependencies (Node built-ins and standard browser APIs only) |
Not guaranteed: 100% exhaustiveness for every input, or convergence inside budget for highly pathological systems. That is the honest floor of numerical mathematics ("guaranteeing all solutions" is undecidable in the general case), not a defect to be fixed.
The machine-readable description for AI agents lives at llms.txt.
Three of the design docs are in English; the deep-dive docs (design rationale, technical reference, licence and pricing, contract, versioning, history) are still in their original Chinese. Each row below tells you which is which.
| Doc | Language | Contents |
|---|---|---|
| 01 · Product role | EN | what it is, what problem it solves, who it is for, capabilities and limits, official wording |
| 02 · User guide | EN | the three forms, the MCP tool contract (input/output/errors), self-hosting, FAQ |
| 05 · Use cases | EN | applicable scenarios (agent backend / multi-agent / off-chain computation / tax and finance control / on-prem / education / audit) and the ones that do not apply |
| 03 · Design ideas | 中文 | six design principles, why it is trustworthy, why no LLM, what it deliberately refuses to do |
| 04 · Technical reference | 中文 | mathematical framework, algorithm pipeline, operator table, hard spec constraints, test suite |
| 06 · Commercial licence and pricing | 中文 | licence model, what is free, hosted-endpoint metering, enterprise annual licence, invoicing |
| 07 · Licence contract | 中文 | commercial licence template, clause walkthrough, signing flow |
| 08 · Versioning | 中文 | version semantics, release flow and the consistency checklist, compatibility promises, history |
| 09 · Project history | 中文 | how it got from the original problem to where it stands now |
If you read only one page, read 01 · Product role — it states the limits and the approved wording.
Privacy and security commitments are published separately: privacy.html.
Free for non-commercial use; commercial use requires written permission (a proprietary licence of our own, not an open-source licence):
1.0.4. Versions 1.0.3 and earlier remain under
the Apache License 2.0 as published at the time (a historical fact, not revocable, and it does not extend
to later versions).Full terms in LICENSE · scope and pricing in 06 · Commercial licence and pricing · contract in 07 · Licence contract
FAQs
Lingshu Solver — the certified deterministic (non-LLM) compute layer for AI agents: real equation systems (≤6 vars) and polynomial roots with Krawczyk interval certification and per-result trust tiers. The tool agents call instead of computing arithmetic
The npm package lingshu-solver receives a total of 319 weekly downloads. As such, lingshu-solver popularity was classified as not popular.
We found that lingshu-solver demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.

Research
/Security News
A new GhostAction wave hits hundreds of GitHub repos, expanding CI/CD secret theft to cloud and AI credentials in source code and git history.

Research
/Security News
Tensorlake npm SDK version 0.5.144 was compromised in a ChainDrop / Shai-Hulud attack, delivering credential-stealing malware.