{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PDUNZKPRMXNWJKWV3UX3BG2TTR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7ad63f1b6444a7748180f19f0a1b5e0d5b474e8a6978a0f79c6625d5ac45427d","cross_cats_sorted":["physics.chem-ph","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-22T20:29:41Z","title_canon_sha256":"88d3d6322f350cc1fafe84dfeaff625e264769757c9ed285613fee5c785e4177"},"schema_version":"1.0","source":{"id":"2604.21069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.21069","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.21069v1","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21069","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"PDUNZKPRMXNW","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"PDUNZKPRMXNWJKWV","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"PDUNZKPR","created_at":"2026-05-26T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:508c27ba8dc5841debd4ecbf233e3a4517aa528af2289891e883a5421912ebd4","target":"graph","created_at":"2026-05-26T01:03:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the machine learning models trained on limited DFT data can generalize accurately to new defect configurations and materials not seen in training."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy."}],"snapshot_sha256":"8b5d49e32791dc2e19d4e68324fe9e08747b989885da003b2f683df4190c1a9d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.21069/integrity.json","findings":[],"snapshot_sha256":"68ca2cd1eceb18c6d16d3a7a66bdf56d1e1144c9b677031d71a172265b4f8036","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arun Mannodi-Kanakkithodi, Menglin Huang, Prashun Gorai, Se\\'an R. Kavanagh","cross_cats":["physics.chem-ph","physics.comp-ph"],"headline":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-22T20:29:41Z","title":"Accelerating point defect simulations using data-driven and machine learning approaches"},"references":{"count":143,"internal_anchors":0,"resolved_work":143,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"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","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Perspective on defect control in semiconductors for photovoltaics,","work_id":"bf74c709-1f28-460b-8147-e644c51916c8","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The defect challenge of wide-bandgap semiconductors for photovoltaics and beyond,","work_id":"65f9dd48-f3d8-44dc-9569-f347f2b669bc","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Pycdt: A python toolkit for modeling point defects in semiconductors and insulators,","work_id":"e2a321a5-c349-4cd1-905a-188733fa4076","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Point defect engineering in thin-film solar cells,","work_id":"b47513a1-57da-4cba-9dba-ebd9d9db2452","year":2018}],"snapshot_sha256":"db830fd9e1100f067affcb1dcfed8d2a83a7822e6effa7fca567737ef437f2b0"},"source":{"id":"2604.21069","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-09T23:26:20.587538Z","id":"cf8140b9-a412-4540-92c9-3d2eff6b7800","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Data-driven machine learning models trained on DFT calculations accelerate point defect simulations while retaining quantum-mechanical accuracy.","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.","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."}},"verdict_id":"cf8140b9-a412-4540-92c9-3d2eff6b7800"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:00b3e09f1cee952c50db8712010322ff661c8420569e68c2617266d00c5d2e5b","target":"record","created_at":"2026-05-26T01:03:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7ad63f1b6444a7748180f19f0a1b5e0d5b474e8a6978a0f79c6625d5ac45427d","cross_cats_sorted":["physics.chem-ph","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-22T20:29:41Z","title_canon_sha256":"88d3d6322f350cc1fafe84dfeaff625e264769757c9ed285613fee5c785e4177"},"schema_version":"1.0","source":{"id":"2604.21069","kind":"arxiv","version":1}},"canonical_sha256":"78e8dca9f165db64aad5dd2fb09b539c6ab46c6ddccc04b4f0612e1c40456851","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e8dca9f165db64aad5dd2fb09b539c6ab46c6ddccc04b4f0612e1c40456851","first_computed_at":"2026-05-26T01:03:30.907683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:30.907683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MyZAHbg5jkrBNy5FGQHX4njzbxK9qhMeMM+og4jkBwBloKl26sTREZBEmUzc7kC/PBnU7K0CB9nygOoP3XRFAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:30.909006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.21069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00b3e09f1cee952c50db8712010322ff661c8420569e68c2617266d00c5d2e5b","sha256:508c27ba8dc5841debd4ecbf233e3a4517aa528af2289891e883a5421912ebd4"],"state_sha256":"a7e31591ddd6126e3392ef0aca6af0971ef512d100dc854052976c15b90d60fa"}