{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EZICFSMDWSLJQH47FFYYIH5DK3","short_pith_number":"pith:EZICFSMD","schema_version":"1.0","canonical_sha256":"265022c983b496981f9f2971841fa356cba1473efc7327d562faa23e3824d114","source":{"kind":"arxiv","id":"2307.15714","version":1},"attestation_state":"computed","paper":{"title":"Synthetic pre-training for neural-network interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"John L. A. Gardner, Kathryn T. Baker, Volker L. Deringer","submitted_at":"2023-07-24T17:16:24Z","abstract_excerpt":"Machine learning (ML) based interatomic potentials have transformed the field of atomistic materials modelling. However, ML potentials depend critically on the quality and quantity of quantum-mechanical reference data with which they are trained, and therefore developing datasets and training pipelines is becoming an increasingly central challenge. Leveraging the idea of \"synthetic\" (artificial) data that is common in other areas of ML research, we here show that synthetic atomistic data, themselves obtained at scale with an existing ML potential, constitute a useful pre-training task for neur"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.15714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2023-07-24T17:16:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"081e3ef087879aede2ebd4e5abd190de1bacad390cc28571c88f23e650e902c8","abstract_canon_sha256":"8c4a5d498204f8a0c7096755e0d4b9b5f4c36a74cc31d291809adabc5f018c82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:39.232190Z","signature_b64":"yiriXb2vfIeWP7BjL8hCGmaThTZUQH5FQWtWf25VOkNNtI5fsHDfLDK8g8QmzdxYDQNGRpqmAQPcitn2ZI5EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"265022c983b496981f9f2971841fa356cba1473efc7327d562faa23e3824d114","last_reissued_at":"2026-07-05T06:35:39.231725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:39.231725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic pre-training for neural-network interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"John L. A. Gardner, Kathryn T. Baker, Volker L. Deringer","submitted_at":"2023-07-24T17:16:24Z","abstract_excerpt":"Machine learning (ML) based interatomic potentials have transformed the field of atomistic materials modelling. However, ML potentials depend critically on the quality and quantity of quantum-mechanical reference data with which they are trained, and therefore developing datasets and training pipelines is becoming an increasingly central challenge. Leveraging the idea of \"synthetic\" (artificial) data that is common in other areas of ML research, we here show that synthetic atomistic data, themselves obtained at scale with an existing ML potential, constitute a useful pre-training task for neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15714","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.15714/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":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":"2307.15714","created_at":"2026-07-05T06:35:39.231781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15714v1","created_at":"2026-07-05T06:35:39.231781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15714","created_at":"2026-07-05T06:35:39.231781+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZICFSMDWSLJ","created_at":"2026-07-05T06:35:39.231781+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZICFSMDWSLJQH47","created_at":"2026-07-05T06:35:39.231781+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZICFSMD","created_at":"2026-07-05T06:35:39.231781+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/EZICFSMDWSLJQH47FFYYIH5DK3","json":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3.json","graph_json":"https://pith.science/api/pith-number/EZICFSMDWSLJQH47FFYYIH5DK3/graph.json","events_json":"https://pith.science/api/pith-number/EZICFSMDWSLJQH47FFYYIH5DK3/events.json","paper":"https://pith.science/paper/EZICFSMD"},"agent_actions":{"view_html":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3","download_json":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3.json","view_paper":"https://pith.science/paper/EZICFSMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15714&json=true","fetch_graph":"https://pith.science/api/pith-number/EZICFSMDWSLJQH47FFYYIH5DK3/graph.json","fetch_events":"https://pith.science/api/pith-number/EZICFSMDWSLJQH47FFYYIH5DK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3/action/storage_attestation","attest_author":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3/action/author_attestation","sign_citation":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3/action/citation_signature","submit_replication":"https://pith.science/pith/EZICFSMDWSLJQH47FFYYIH5DK3/action/replication_record"}},"created_at":"2026-07-05T06:35:39.231781+00:00","updated_at":"2026-07-05T06:35:39.231781+00:00"}