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.
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.
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.
MatterSpace supports four campaign modes, each addressing a distinct discovery scenario:
| Campaign Mode | Objective | Target Knowledge |
|---|---|---|
| Open Discovery | Explore novel compositions and structures without a predefined target | None — unconstrained search |
| Prototype Optimization | Improve a known candidate structure toward better performance | Starting structure provided |
| Guided Rediscovery | Rediscover a known target with partial structural hints | Partial constraints provided |
| Blind Rediscovery Benchmark | Recover a sealed target with zero structural information | None — 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.
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:
| # | Workflow | Target Applications |
|---|---|---|
| 1 | magnets | Permanent magnets, magnetic storage, spintronic devices |
| 2 | battery_cathodes | Li-ion and post-Li cathode materials |
| 3 | solid_electrolytes | Solid-state battery electrolytes |
| 4 | catalysis | Heterogeneous catalysts, SAA catalysts, electrocatalysts |
| 5 | thermoelectrics | Waste-heat recovery, Peltier devices |
| 6 | photovoltaics | Solar cell absorbers, transparent conductors |
| 7 | high_entropy_alloys | Multi-principal-element alloys, extreme-environment materials |
| 8 | superconductors | High-Tc superconductors, quantum computing materials |
| 9 | thermal_barrier_coatings | Turbine 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 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.
| Target | Level A (50 candidates) | Level B (50 candidates) | Best RMSD | Status |
|---|---|---|---|---|
| Re₁@Ni(111)+CH₄ | 50 / 50 pass | 26 / 50 pass | 655 mÅ | ✓ PASS |
| Ir₁@Ni(111)+CH₄ | 50 / 50 pass | 30 / 50 pass | 508 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.
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 limitations:
Current focus: