Innovation & Tech

ForShor.ai Launches Lean-Verified AI Circuit Design Challenge

Launched Nov. 18, ForShor.ai requires AI-proposed Shor’s algorithm circuits to pass Lean 4 proofs before earning leaderboard credit, without claiming hardware readiness.

By Daniel Okafor

5 min read

Zapata and UMD Launch ForShor for Verified AI-Assisted Quantum Research
Zapata and UMD Launch ForShor for Verified AI-Assisted Quantum Researchpapazachariasa / pixabay

What's News

  • Zapata Quantum and UMD announced ForShor.ai on November 18.
  • The preprint was submitted November 16 by Anirudh Suresh, Joshua M. Courtney, Runzhou Tao, and Yudong Cao.
  • AI-proposed circuits must pass Lean 4 proofs before earning leaderboard credit.
  • Reported gate-cost scaling is O(n^(2+ε)), with n as input size and ε positive.
  • The framework checks three areas: mathematical correctness, gate-cost growth, and detailed-circuit translation.

By Daniel Okafor

Zapata Quantum and the University of Maryland announced ForShor.ai on November 18, requiring AI-proposed Shor’s algorithm circuits to pass Lean 4 formal proofs before earning leaderboard credit.

The open challenge, built around a formally verified implementation of Shor’s algorithm, lets researchers use AI to propose improvements, submit solutions to a leaderboard, and inspect documentation linking the mathematics to machine-checked proofs. Zapata Quantum and UMD said it extends their collaboration and is intended to test verification methods relevant to Zapata Quantum’s Quantum Pilot software platform.

What problem does ForShor.ai solve?

Zapata Quantum and UMD said the project addresses a weakness in AI-driven science: generating a plausible algorithm or explanation is easier than proving it correct.

ForShor places AI search inside explicit mathematical constraints and leaves researchers responsible for understanding the results. It gives them a defined optimization problem with checkable conditions rather than asking an AI system to invent an entirely new quantum algorithm without limits.

Why start with Shor’s algorithm?

Shor’s algorithm is best known for its cryptographic implications. Its quantum component can find a repeating structure, called an order, in modular arithmetic, UMD’s project description says. Classical mathematical steps can then use that result to help factor a large integer.

ForShor focuses on the arithmetic circuits behind that computation. It does not ask whether quantum hardware can factor large numbers. The University of Maryland’s project description identifies fast Toom–Cook multiplication as a key building block.

That method breaks a large multiplication problem into smaller pieces, creating choices about how to organize the arithmetic. Those choices affect the number of gates and working qubits a circuit needs. A gate is an operation in a quantum circuit; a logical qubit is a unit of quantum information at the algorithmic level. Reducing either requirement can improve a design’s prospects, although physical hardware adds further costs.

How does the framework check AI proposals?

The ForShor preprint, submitted November 16 by Anirudh Suresh, Joshua M. Courtney, Runzhou Tao, and Yudong Cao, describes a harness that accepts a design specification called a policy. A policy defines choices in a recursive circuit construction and can come from a human researcher or an AI agent.

The preprint groups the verification into three connected claims:

  • Mathematical correctness of the implementation.
  • Asymptotic growth of its gate cost.
  • Correct translation of the verified algorithm into a more detailed circuit representation.

The preprint reports gate-cost scaling of O(n^(2+ε)), where n describes input size and ε is positive. That formula describes how cost grows as the problem gets larger. It does not mean a particular 2,048-bit instance can run with a small, fixed number of gates.

The implementation uses Lean 4 formal proofs. Researchers state required behavior precisely and supply proofs that a proof assistant can check. Compared with testing a program on selected examples, the guarantees remain tied to the definitions and assumptions being proved.

The project’s interactive proof documentation links arithmetic choices to the larger order-finding circuit. It connects explanations and diagrams to corresponding Lean code, allowing researchers to inspect the argument at different levels.

One part of the design space concerns instruction tables for recursive multiplication. Different arrangements of additions, shifts, and related operations can change a circuit’s cost. A proposed table must satisfy the framework’s admissibility conditions before it can inherit the relevant correctness guarantees.

That separation lets an AI agent explore candidate arrangements or suggest optimizations while an independently checkable contract determines validity. Researchers can then study why a successful candidate works instead of treating its leaderboard score as the only output.

Peter Shor, the algorithm’s creator and a member of Zapata Quantum’s Scientific Advisory Board, said: “ForShor puts formal verification, with humans in the loop, at the center of that process.”

How does ForShor connect to Quantum Pilot?

Yudong Cao, Zapata Quantum’s chief technology officer, characterized the initiative as a white-box learning and research environment. The public challenge includes a leaderboard and community resources, and Zapata Quantum says contributors may become co-authors of a subsequent research paper.

ForShor sits within Zapata Quantum’s broader effort to make quantum application development more systematic. The company says Quantum Pilot combines a knowledge layer, computational tools, and verification workflows. Its three named components perform distinct jobs:

  • Quantum Graph connects applications, algorithms, research, and hardware roadmaps.
  • Quantum Engine handles algorithm selection, resource estimation, experiment design, and benchmarking.
  • Quantum Assurance combines formal methods with expert review before results inform a decision.

Resource estimation asks what an algorithm would require to execute. A mathematically valid design can still demand more qubits or runtime than an available machine can provide. Linking the estimate to the verified implementation helps prevent researchers from proving one circuit correct while estimating the resource needs of a different one, Zapata Quantum said.

As Unite.AI reported in earlier Quantum Pilot coverage, the platform is intended to connect potential use cases with technical feasibility and comparisons against classical computing. Zapata Quantum says ForShor will serve as a proving ground for verification methods used in that wider process.

Does the proof establish hardware readiness?

No. ForShor provides an inspectable software and mathematics framework. It does not show that current quantum processors can factor cryptographically significant numbers or remove the engineering demands of fault-tolerant computing, the project materials said.

Physical error rates, error correction, hardware connectivity, and execution time remain separate considerations. A machine-checked proof establishes a stated mathematical result; researchers still need clear definitions, documentation, and review to understand it.

The broader research model lets AI explore designs aggressively while requiring proposals to pass explicit, reproducible checks. ForShor supplies a defined quantum task, an open implementation, and a community able to inspect both candidate designs and the reasoning behind them. The next measure of success is whether AI-generated improvements can survive both formal proof and Quantum Pilot’s resource analysis. Zapata Quantum says ForShor will test the verification methods connecting those two steps.

Source: unite.ai

Share this article:

More from Daniel Okafor

Daniel Okafor

Show full bio

Correspondent covering money, funding and market shifts around entrepreneurship, startups and venture funding at Business Bearings.

2,391 articles

Related articles

« Previous articleNext article »