Autonomous ML search and experiments find Fe–Co–Ir/Pt alloys above the Slater–Pauling magnetization limit
A game-tree search using Gaussian-process predictions and first-principles calculations proposed dilute Ir and Pt additions as a counterintuitive way to raise Fe–Co magnetization. Combinatorial sputtering and magnetic measurements experimentally found Fe–Co–Ir and Fe–Co–Pt compositions with magnetization exceeding the conventional Fe₃Co₁ Slater–Pauling limit; the highest-moment points reported in the ternary maps were near Fe₈₁Co₁₅Ir₄ and Fe₈₅Co₁₁Pt₄. The study’s calculations attribute the effect to Ir/Pt-induced increases in local Fe and Co moments.
Technology: Autonomous materials search using a Gaussian-process regression model with game-tree search and an upper-confidence-bound acquisition rule, coupled to KKR-CPA first-principles calculations
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: A game-tree search using Gaussian-process predictions and first-principles calculations proposed dilute Ir and Pt additions as a counterintuitive way to raise Fe–Co magnetization.
- Still unknown: The highest-moment composition suggested by the autonomous search (Fe₈₂Co₁₃Ir₄Pt₁) was not itself the maximum in the measured ternary composition spreads; the Fe–Co–Ir and Fe–Co–Pt maps identified different peak compositions. The finding is based on sputtered, annealed thin-film composition spreads and room-temperature MOKE/SQUID measurements, not bulk ingots or device testing. The eight-element search space was narrowed by preliminary calculations. KKR-CPA results assume ideal disordered bulk states at 0 K, unlike the film measurements.
- AI role: The autonomous system iteratively selected compositions in an eight-component disordered-alloy search using ab-initio magnetic-moment estimates and a game-tree Gaussian-process model balancing exploration and exploitation. After about 43 days it proposed Fe₈₂Co₁₃Ir₄Pt₁; that hypothesis directed combinatorial synthesis and testing of Fe–Co–Ir and Fe–Co–Pt spreads. The follow-up measurements found compositions surpassing the prior Fe₃Co₁ benchmark and motivated theoretical analysis of impurity-enhanced Fe/Co local moments.
Evidence sources: https://www.nature.com/articles/s43246-021-00135-0
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: at percentile 90 of works of the same type, year and subfield (OpenAlex work metrics, 56 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.