{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PDUNZKPRMXNWJKWV3UX3BG2TTR","short_pith_number":"pith:PDUNZKPR","schema_version":"1.0","canonical_sha256":"78e8dca9f165db64aad5dd2fb09b539c6ab46c6ddccc04b4f0612e1c40456851","source":{"kind":"arxiv","id":"2604.21069","version":1},"attestation_state":"computed","paper":{"title":"Accelerating point defect simulations using data-driven and machine learning approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy.","cross_cats":["physics.chem-ph","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Arun Mannodi-Kanakkithodi, Menglin Huang, Prashun Gorai, Se\\'an R. Kavanagh","submitted_at":"2026-04-22T20:29:41Z","abstract_excerpt":"Point defects in solid-state materials are now routinely simulated using large supercell structures, requiring efficient quantum mechanical solutions. Data-driven and machine learning (ML) models trained on computational data can enable rapid defect property predictions and high-throughput screening. In this article, we provide an overview of prominent efforts to accelerate defect simulations using these approaches. We begin by discussing the motivations for data-driven techniques in defect modeling, and describe efforts over the past decade to use descriptor-based models for rapid screening o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.21069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-22T20:29:41Z","cross_cats_sorted":["physics.chem-ph","physics.comp-ph"],"title_canon_sha256":"88d3d6322f350cc1fafe84dfeaff625e264769757c9ed285613fee5c785e4177","abstract_canon_sha256":"7ad63f1b6444a7748180f19f0a1b5e0d5b474e8a6978a0f79c6625d5ac45427d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:30.909006Z","signature_b64":"MyZAHbg5jkrBNy5FGQHX4njzbxK9qhMeMM+og4jkBwBloKl26sTREZBEmUzc7kC/PBnU7K0CB9nygOoP3XRFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e8dca9f165db64aad5dd2fb09b539c6ab46c6ddccc04b4f0612e1c40456851","last_reissued_at":"2026-05-26T01:03:30.907683Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:30.907683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating point defect simulations using data-driven and machine learning approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy.","cross_cats":["physics.chem-ph","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Arun Mannodi-Kanakkithodi, Menglin Huang, Prashun Gorai, Se\\'an R. Kavanagh","submitted_at":"2026-04-22T20:29:41Z","abstract_excerpt":"Point defects in solid-state materials are now routinely simulated using large supercell structures, requiring efficient quantum mechanical solutions. Data-driven and machine learning (ML) models trained on computational data can enable rapid defect property predictions and high-throughput screening. In this article, we provide an overview of prominent efforts to accelerate defect simulations using these approaches. We begin by discussing the motivations for data-driven techniques in defect modeling, and describe efforts over the past decade to use descriptor-based models for rapid screening o"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Surrogate models and interatomic potentials trained on density functional theory data lead to predictions with quantum-mechanical accuracies at a fraction of the cost, including for phonon modes and vibrational free energies at finite temperatures.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the machine learning models trained on limited DFT data can generalize accurately to new defect configurations and materials not seen in training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Machine learning models trained on quantum mechanical data can predict defect properties in solids with high accuracy but at much lower computational cost than traditional methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8b5d49e32791dc2e19d4e68324fe9e08747b989885da003b2f683df4190c1a9d"},"source":{"id":"2604.21069","kind":"arxiv","version":1},"verdict":{"id":"cf8140b9-a412-4540-92c9-3d2eff6b7800","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T23:26:20.587538Z","strongest_claim":"Surrogate models and interatomic potentials trained on density functional theory data lead to predictions with quantum-mechanical accuracies at a fraction of the cost, including for phonon modes and vibrational free energies at finite temperatures.","one_line_summary":"Machine learning models trained on quantum mechanical data can predict defect properties in solids with high accuracy but at much lower computational cost than traditional methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the machine learning models trained on limited DFT data can generalize accurately to new defect configurations and materials not seen in training.","pith_extraction_headline":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.21069/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T13:38:05.276058Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T01:20:45.505796Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"68ca2cd1eceb18c6d16d3a7a66bdf56d1e1144c9b677031d71a172265b4f8036"},"references":{"count":143,"sample":[{"doi":"","year":2022,"title":"L. Vines, E. Monakhov, and A. Kuznetsov, “Defects in semiconductors,” Journal of Applied Physics, vol. 132, p. 150401, 10 2022","work_id":"ecc12e56-12b3-41b2-83ea-90ad182f2c8e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Perspective on defect control in semiconductors for photovoltaics,","work_id":"bf74c709-1f28-460b-8147-e644c51916c8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"The defect challenge of wide-bandgap semiconductors for photovoltaics and beyond,","work_id":"65f9dd48-f3d8-44dc-9569-f347f2b669bc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Pycdt: A python toolkit for modeling point defects in semiconductors and insulators,","work_id":"e2a321a5-c349-4cd1-905a-188733fa4076","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Point defect engineering in thin-film solar cells,","work_id":"b47513a1-57da-4cba-9dba-ebd9d9db2452","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":143,"snapshot_sha256":"db830fd9e1100f067affcb1dcfed8d2a83a7822e6effa7fca567737ef437f2b0","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.21069","created_at":"2026-05-26T01:03:30.907820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.21069v1","created_at":"2026-05-26T01:03:30.907820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21069","created_at":"2026-05-26T01:03:30.907820+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDUNZKPRMXNW","created_at":"2026-05-26T01:03:30.907820+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDUNZKPRMXNWJKWV","created_at":"2026-05-26T01:03:30.907820+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDUNZKPR","created_at":"2026-05-26T01:03:30.907820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR","json":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR.json","graph_json":"https://pith.science/api/pith-number/PDUNZKPRMXNWJKWV3UX3BG2TTR/graph.json","events_json":"https://pith.science/api/pith-number/PDUNZKPRMXNWJKWV3UX3BG2TTR/events.json","paper":"https://pith.science/paper/PDUNZKPR"},"agent_actions":{"view_html":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR","download_json":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR.json","view_paper":"https://pith.science/paper/PDUNZKPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.21069&json=true","fetch_graph":"https://pith.science/api/pith-number/PDUNZKPRMXNWJKWV3UX3BG2TTR/graph.json","fetch_events":"https://pith.science/api/pith-number/PDUNZKPRMXNWJKWV3UX3BG2TTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR/action/storage_attestation","attest_author":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR/action/author_attestation","sign_citation":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR/action/citation_signature","submit_replication":"https://pith.science/pith/PDUNZKPRMXNWJKWV3UX3BG2TTR/action/replication_record"}},"created_at":"2026-05-26T01:03:30.907820+00:00","updated_at":"2026-05-26T01:03:30.907820+00:00"}