{"paper":{"title":"Machine learning potential as a guide for eutectic in ultra-refractory multicomponent ceramics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A neural-network interatomic potential locates eutectic compositions in ultra-refractory alloys by simulating only the liquid phase.","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cond-mat.dis-nn","authors_text":"A.V. Mikheyenkov, E.A. Levashov, N.M. Chtchelkatchev, V.E. Valiulin","submitted_at":"2026-05-15T15:48:27Z","abstract_excerpt":"The experimental determination of eutectic points is a long-established and widely used technique, but it is generally only practical for systems with relatively low melting points. Many modern, promising materials, however, are ultra-refractory, with melting points exceeding 3000 K. For these systems, conventional melting experiments become prohibitively expensive and technically challenging. Advanced AI modeling can serve as a powerful precursor to guide successful experimentation in such cases. This work proposes a novel criterion for determining the eutectic point concentration in ultra-re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The core of the algorithm is a machine-learning interatomic potential, based on a neural network, which achieves accuracy comparable to ab initio methods. Crucially, the algorithm operates effectively in the liquid phase, eliminating the need for information about the solid alloy's crystalline structure to estimate eutectic points.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The machine-learning potential trained on the Ti-B-C system accurately captures the liquid-phase thermodynamics needed to locate the true eutectic composition, and the proposed criterion derived from it is transferable to other ultra-refractory multicomponent systems.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A neural-network machine learning interatomic potential is used to estimate eutectic points in high-melting alloys by operating directly in the liquid phase without solid-structure input, demonstrated on the Ti-B-C system.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A neural-network interatomic potential locates eutectic compositions in ultra-refractory alloys by simulating only the liquid phase.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e3b857bdd5fee68c0ac6d321d920a04fbde533fdef5e3421f2415330e80e4562"},"source":{"id":"2605.16091","kind":"arxiv","version":1},"verdict":{"id":"4f90e05b-d8b6-40cd-9a54-8bbb04893ec3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:13:12.588292Z","strongest_claim":"The core of the algorithm is a machine-learning interatomic potential, based on a neural network, which achieves accuracy comparable to ab initio methods. Crucially, the algorithm operates effectively in the liquid phase, eliminating the need for information about the solid alloy's crystalline structure to estimate eutectic points.","one_line_summary":"A neural-network machine learning interatomic potential is used to estimate eutectic points in high-melting alloys by operating directly in the liquid phase without solid-structure input, demonstrated on the Ti-B-C system.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The machine-learning potential trained on the Ti-B-C system accurately captures the liquid-phase thermodynamics needed to locate the true eutectic composition, and the proposed criterion derived from it is transferable to other ultra-refractory multicomponent systems.","pith_extraction_headline":"A neural-network interatomic potential locates eutectic compositions in ultra-refractory alloys by simulating only the liquid phase."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16091/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.528601Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.430322Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:26:19.229074Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.496874Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a4f0fff01411e54984daca5d789d77d0a5791e02d3fd9a322e935b1b58726fc5"},"references":{"count":97,"sample":[{"doi":"","year":null,"title":"This approach enabled systematic sampling across the entire concentration space","work_id":"581dc123-a7d2-4358-99ad-f37ee9e37b2b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2000,"title":"Kurchatov In- stitute","work_id":"0c6b0e61-2637-4648-9976-ee8a5d626217","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"White, Takashi Goto, and Eliz- abeth C","work_id":"4640f7be-94ca-4b40-ac9e-fe0e39cfe43e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Pollock, Dierk Raabe, Marc Andr´ e Meyers, Assel Aitkaliyeva, Kerri-Lee Chintersingh, Zachary C","work_id":"79913e83-cee5-4772-b51a-df3fb770176d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Schreiber, Ruth Schwaiger, Martin Heilmaier, and Scott J","work_id":"860e15cd-cf02-4cb8-b7cf-0f9cb52023bc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":97,"snapshot_sha256":"f1679af5527cdbd9534449bb3db69927f38f83546fe03927bbcc54a56dad5e6f","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}