A survey of published research, from the Essentia Memoria newsroom. It lists real papers, each looked up at its DOI registry; the game has not repeated their results.

Research survey

What AI research has found: new materials

Happened: October 28, 2026 at 10:30 PM UTC · Published: October 28, 2026 at 10:30 PM UTC

12 published works on new materials, each looked up at its DOI registry before it was listed here, with what each one reports in plain words.

Watch

Explanatory visualisation, drawn from the record's numbers. It is not footage of the event: nobody filmed it.

Listen

Transcript

News from the Essentia Memoria game universe. What AI research has found: new materials. 12 published works on new materials, each looked up at its DOI registry before it was listed here, with what each one reports in plain words. This survey lists what each paper reports. The game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited. This report was written from the world record by a fixed template. The full story and its source records are on essentiamemoria.com.

The question

Can a model propose crystals and materials nobody has made yet?

Claims, and where each one comes from

Where this research lives in the game (a place the world grammar builds)laboratory → laboratory
Game simulation · Set in code src/lib/world-grammar/place-grammar.ts · resolvePurpose('laboratory')
Published works in this survey, each resolved at its DOI registry12
Real-world knowledge · Source [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12]
Graph networks proposed a very large number of crystal structures predicted to be stable; human chemists still have to make and test them.Merchant 2023
Real-world knowledge · Source [1]
Developing an improved crystal graph convolutional neural network framework for accelerated materials discoveryPark 2020
Real-world knowledge · Source [2]
Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discoveryRosen 2021
Real-world knowledge · Source [3]
Crystal Structure Prediction via Deep LearningRyan 2018
Real-world knowledge · Source [4]
Materials discovery and design using machine learningLiu 2017
Real-world knowledge · Source [5]
Accelerating materials discovery using artificial intelligence, high performance computing and roboticsPyzer‐Knapp 2022
Real-world knowledge · Source [6]
Evaluating explorative prediction power of machine learning algorithms for materials discovery using k -fold forward cross-validationXiong 2019
Real-world knowledge · Source [7]
Genetic algorithms for computational materials discovery accelerated by machine learningJennings 2019
Real-world knowledge · Source [8]
Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discoveryMeredig 2018
Real-world knowledge · Source [9]
Accelerating materials discovery using machine learningJuan 2020
Real-world knowledge · Source [10]
Universal fragment descriptors for predicting properties of inorganic crystalsIsayev 2017
Real-world knowledge · Source [11]
On-the-fly closed-loop materials discovery via Bayesian active learningKusne 2020
Real-world knowledge · Source [12]

References, checked at their registry

[1] Merchant (2023). Scaling deep learning for materials discovery. Nature. doi:10.1038/s41586-023-06735-9
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Scaling deep learning for materials discovery” (2023)
[2] Park (2020). Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. Physical Review Materials. doi:10.1103/physrevmaterials.4.063801
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery” (2020)
[3] Rosen (2021). Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery. Matter. doi:10.1016/j.matt.2021.02.015
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery” (2021)
[4] Ryan (2018). Crystal Structure Prediction via Deep Learning. Journal of the American Chemical Society. doi:10.1021/jacs.8b03913
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Crystal Structure Prediction via Deep Learning” (2018)
[5] Liu (2017). Materials discovery and design using machine learning. Journal of Materiomics. doi:10.1016/j.jmat.2017.08.002
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Materials discovery and design using machine learning” (2017)
[6] Pyzer‐Knapp (2022). Accelerating materials discovery using artificial intelligence, high performance computing and robotics. npj Computational Materials. doi:10.1038/s41524-022-00765-z
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Accelerating materials discovery using artificial intelligence, high performance computing and robotics” (2022)
[7] Xiong (2019). Evaluating explorative prediction power of machine learning algorithms for materials discovery using k -fold forward cross-validation. Computational Materials Science. doi:10.1016/j.commatsci.2019.109203
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Evaluating explorative prediction power of machine learning algorithms for materials discovery using <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.svg"> <mml:mrow> <mml:mi>k</mml:mi> </mml:mrow> </mml:math> -fold forward cross-validation” (2020)
[8] Jennings (2019). Genetic algorithms for computational materials discovery accelerated by machine learning. npj Computational Materials. doi:10.1038/s41524-019-0181-4
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Genetic algorithms for computational materials discovery accelerated by machine learning” (2019)
[9] Meredig (2018). Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery. Molecular Systems Design & Engineering. doi:10.1039/c8me00012c
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery” (2018)
[10] Juan (2020). Accelerating materials discovery using machine learning. Journal of Material Science and Technology. doi:10.1016/j.jmst.2020.12.010
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Accelerating materials discovery using machine learning” (2021)
[11] Isayev (2017). Universal fragment descriptors for predicting properties of inorganic crystals. Nature Communications. doi:10.1038/ncomms15679
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “Universal fragment descriptors for predicting properties of inorganic crystals” (2017)
[12] Kusne (2020). On-the-fly closed-loop materials discovery via Bayesian active learning. Nature Communications. doi:10.1038/s41467-020-19597-w
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:30 PM UTC · the registry holds “On-the-fly closed-loop materials discovery via Bayesian active learning” (2020)

Review

Not peer reviewed. No human scientist has reviewed this survey. Its template and landmark summaries were written with an AI assistant (Claude); the papers it lists are real and each was checked at its registry, so anyone can follow the links and read them.

Each listed DOI was resolved, and its title, year and first author matched the listing.
Each work the search found is held by Crossref, a registry independent of the search.
Each number in the headline and summary is accounted for by a listed claim.
No candidate work was dropped: every one the desk found or named was confirmed by its registry.

Code version: fa127b6f988c

What the record does not say

This survey lists what each paper reports; the game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited.

How this was written

Landmark works named by the desk, then the most-cited works with a DOI that OpenAlex returns when titles and abstracts are searched for ("materials discovery" OR "crystal structure prediction" OR "inorganic crystals") AND ("machine learning" OR "deep learning" OR "neural network" OR "neural networks" OR "artificial intelligence" OR convolutional OR "reinforcement learning" OR "language model" OR transformer); a hit is kept only if its own title names the field and its title or abstract names an AI method, as whole words, and the hits that name the most of these words in their title come first. Each candidate was looked up at Crossref (OpenAlex as second resolver) and its title, year and first author compared; a work the search found is shown only when Crossref holds it. Landmark summaries were written by the desk; the other works are listed by their own titles.

Source records: code:src/lib/world-grammar/place-grammar.ts#resolvePurpose · doi:10.1038/s41586-023-06735-9 · doi:10.1103/physrevmaterials.4.063801 · doi:10.1016/j.matt.2021.02.015 · doi:10.1021/jacs.8b03913 · doi:10.1016/j.jmat.2017.08.002 · doi:10.1038/s41524-022-00765-z · doi:10.1016/j.commatsci.2019.109203 · doi:10.1038/s41524-019-0181-4 · doi:10.1039/c8me00012c · doi:10.1016/j.jmst.2020.12.010 · doi:10.1038/ncomms15679 · doi:10.1038/s41467-020-19597-w