{"paper":{"title":"Learning Thermoelectric Transport from Crystal Structures via Multiscale Graph Neural Network","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"A multiscale graph neural network estimates electronic transport coefficients in thermoelectric crystals directly from their structures.","cross_cats":["physics.app-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Fang Lyu, Jing Shi, Ling Miao, Tan Peng, Wei Cao, Wenhao Xie, Yijing Zuo, Yue Hou, Yuxuan Zeng, Ziyu Wang","submitted_at":"2025-12-07T07:21:05Z","abstract_excerpt":"Graph neural networks (GNNs) are designed to extract latent patterns from graph-structured data, making them particularly well suited for crystal representation learning. Here, we propose a GNN model tailored for estimating electronic transport coefficients in inorganic thermoelectric crystals. The model encodes crystal structures and physicochemical properties in a multiscale manner, encompassing global, atomic, bond, and angular levels. It achieves state-of-the-art performance on benchmark datasets with remarkable extrapolative capability. By combining the proposed GNN with \\textit{ab initio"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The model achieves state-of-the-art performance on benchmark datasets with remarkable extrapolative capability. By combining the proposed GNN with ab initio calculations, we successfully identify compounds exhibiting outstanding electronic transport properties.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That encoding crystal structures and physicochemical properties in a multiscale manner (global, atomic, bond, and angular levels) is sufficient to capture the underlying physics governing electronic transport coefficients.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A multiscale GNN predicts thermoelectric transport properties from crystal structures, achieves SOTA performance, and identifies promising new compounds via combination with ab initio calculations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A multiscale graph neural network estimates electronic transport coefficients in thermoelectric crystals directly from their structures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ceafbad88c9b5c90a25a4bead6ac1dde0eeb7f0ff6bc269caca29715fe0758f4"},"source":{"id":"2512.06697","kind":"arxiv","version":3},"verdict":{"id":"4ada188b-6581-4043-8896-5dee2381a0ae","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T01:20:53.997822Z","strongest_claim":"The model achieves state-of-the-art performance on benchmark datasets with remarkable extrapolative capability. By combining the proposed GNN with ab initio calculations, we successfully identify compounds exhibiting outstanding electronic transport properties.","one_line_summary":"A multiscale GNN predicts thermoelectric transport properties from crystal structures, achieves SOTA performance, and identifies promising new compounds via combination with ab initio calculations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That encoding crystal structures and physicochemical properties in a multiscale manner (global, atomic, bond, and angular levels) is sufficient to capture the underlying physics governing electronic transport coefficients.","pith_extraction_headline":"A multiscale graph neural network estimates electronic transport coefficients in thermoelectric crystals directly from their structures."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.06697/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ab47f51b149e5e86747dfa1e5923bed4c20692a6ab77419786e3b2bec44aa63d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}