Technical Report

MatterSpace: Hosted Blind Rediscovery of Single-Atom Alloy Catalysts

Faruk Guney

Vareon Inc., Irvine, California, USA

March 2026

Abstract

MatterSpace is a delivered material discovery product built for teams that need candidates under real physical constraints. In blind rediscovery benchmarks on its hosted deployment, MatterSpace recovered Re₁@Ni(111)+CH₄ and Ir₁@Ni(111)+CH₄ single-atom alloy catalysts to sub-angstrom accuracy: 655 milliangstrom and 508 milliangstrom RMSD respectively, both below the 1.00 Å threshold. The product passed all 82 of 82 surface checks spanning API correctness, constraint enforcement, campaign orchestration, and result integrity.

Executive Summary

This document positions MatterSpace as a delivered material discovery product whose central public validation claim is blind rediscovery of two sealed catalyst targets through a hosted deployment. Two sealed targets — Re₁@Ni(111)+CH₄ and Ir₁@Ni(111)+CH₄ — were recovered to sub-angstrom RMSD through the production API, and the deployment passed all 82 of 82 product surface checks covering constraint enforcement, campaign orchestration, validation integrity, and API correctness.

The significance of blind rediscovery as a product validation strategy is straightforward: if a material discovery product can autonomously find known catalysts that human researchers took years to identify, without any target information leaking into the generation process, then its novel discoveries on unknown targets deserve serious scientific consideration. Blind rediscovery is the benchmark that ties public research claims to live, deployable capability.

Product Surface

MatterSpace is built for material and energy workflows. The product starts from target properties, hard constraints, and feasibility requirements, then generates candidates that teams can rank, simulate, and synthesize next.

What matters is not internal implementation detail. What matters is that the system keeps constraint handling inside the workflow, produces viable material candidates, and exposes the product consistently through API, SDK, and agent-facing interfaces.

The benchmark in this report focuses on catalyst rediscovery, but the same material-oriented operating surface extends to batteries, electrolytes, coatings, superconductors, magnets, and related material programs.

Campaign Modes

MatterSpace supports four campaign modes, each addressing a distinct discovery scenario:

Campaign ModeObjectiveTarget Knowledge
Open DiscoveryExplore novel compositions and structures without a predefined targetNone — unconstrained search
Prototype OptimizationImprove a known candidate structure toward better performanceStarting structure provided
Guided RediscoveryRediscover a known target with partial structural hintsPartial constraints provided
Blind Rediscovery BenchmarkRecover a sealed target with zero structural informationNone — sealed reference

Blind Rediscovery Benchmark is the most demanding mode and serves as the product's primary public validation benchmark. In this mode, the generation surface has no access to the target structure, composition, or properties during the discovery process. All comparisons are performed post-hoc against sealed references, ensuring that any match is a genuine independent discovery rather than optimization toward a known answer.

Supported Material Workflows

MatterSpace supports a set of material workflows that encode the relevant physical constraints, validation criteria, property targets, and computational parameters appropriate to each class of materials:

#WorkflowTarget Applications
1magnetsPermanent magnets, magnetic storage, spintronic devices
2battery_cathodesLi-ion and post-Li cathode materials
3solid_electrolytesSolid-state battery electrolytes
4catalysisHeterogeneous catalysts, SAA catalysts, electrocatalysts
5thermoelectricsWaste-heat recovery, Peltier devices
6photovoltaicsSolar cell absorbers, transparent conductors
7high_entropy_alloysMulti-principal-element alloys, extreme-environment materials
8superconductorsHigh-Tc superconductors, quantum computing materials
9thermal_barrier_coatingsTurbine blade coatings, aerospace thermal protection

Each workflow defines the property ranges, scoring criteria, and validation checks appropriate to its material class. The catalysis workflow was used for the blind rediscovery benchmark documented in this report.

Blind Rediscovery Results

Blind rediscovery was executed on the hosted MatterSpace deployment using NVIDIA A10G hardware, showing that the product can achieve research-grade results on production-class cloud GPUs.

TargetLevel A (50 candidates)Level B (50 candidates)Best RMSDStatus
Re₁@Ni(111)+CH₄50 / 50 pass26 / 50 pass655 mÅ✓ PASS
Ir₁@Ni(111)+CH₄50 / 50 pass30 / 50 pass508 mÅ✓ PASS

Both targets achieved 100% Level A pass rates and majority Level B pass rates. The best RMSD values — 655 mÅ for Re₁@Ni and 508 mÅ for Ir₁@Ni — both fall below the 1.00 Å threshold defined for the hosted deployment protocol.

These results were achieved on NVIDIA A10G GPUs, which confirms that MatterSpace's computational requirements are compatible with standard cloud deployment infrastructure for this benchmark class.

Product Interfaces

MatterSpace exposes three public interface surfaces, all providing equivalent access to the product capability:

REST API: The primary programmatic interface. Endpoints are organized around campaigns, candidates, constraints, validation, workflows, and results. Request and response payloads use JSON with typed schemas.

Python SDK: A thin client library wrapping the REST API with Pythonic conventions. It provides typed data classes for campaigns, candidates, and results, and supports both synchronous and asynchronous usage patterns.

Model Context Protocol (MCP): Native MCP integration enabling AI agents to discover and invoke MatterSpace capabilities through a standard tool interface. MCP-compatible agents can inspect schemas and execute material discovery campaigns without custom integration code.

All three interfaces share the same underlying product surface. A campaign launched via the Python SDK produces identical results to one launched via REST or MCP. This interface equivalence is verified as part of the 82/82 product surface checks.

Current Boundaries

Current limitations:

Current focus: