{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JI76WFZ4VRVRRLMMTYOIBEGTH7","short_pith_number":"pith:JI76WFZ4","schema_version":"1.0","canonical_sha256":"4a3feb173cac6b18ad8c9e1c8090d33fc7eaa9e0014595e183a73aad2a727eef","source":{"kind":"arxiv","id":"2106.14583","version":2},"attestation_state":"computed","paper":{"title":"Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Akihide Hayashi, Chikashi Shinagawa, Daisuke Motoki, Hideki ONO, Hiroki Iriguchi, Iori Kurata, Kosuke Nakago, Marc Ong, Nontawat Charoenphakdee, Ryohto Sawada, Ryuichiro Ishitani, So Takamoto, Taiki Yamaguchi, Takafumi Ishii, Takao Kudo, Takeshi Ibuka, Taku Watanabe, Tasuku Onodera, Toshiki Kataoka, Wenwen Li, Yoshihiro Yayama, Yusuke Asano","submitted_at":"2021-06-28T11:32:13Z","abstract_excerpt":"Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. To overcome this issue, we have developed a universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, wh"},"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":"2106.14583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2021-06-28T11:32:13Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"7b588fbbdae9fc1bf6e13750e9d8a99352f8fce6b677b0c91e56fdbae99e0806","abstract_canon_sha256":"f5fef3ec0c42e14c577c3a341dac923c04e55fc2f6d97a2afd415c5205781860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:17.258878Z","signature_b64":"39lT1yqK9I3SjGZjziJs/WRarv+c+3KL4gZXoEGyKmAb/0X/ybDRhayHzyfNGrdAmPjFkwRvTSEjVCtFvhzSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3feb173cac6b18ad8c9e1c8090d33fc7eaa9e0014595e183a73aad2a727eef","last_reissued_at":"2026-07-05T04:37:17.258299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:17.258299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Akihide Hayashi, Chikashi Shinagawa, Daisuke Motoki, Hideki ONO, Hiroki Iriguchi, Iori Kurata, Kosuke Nakago, Marc Ong, Nontawat Charoenphakdee, Ryohto Sawada, Ryuichiro Ishitani, So Takamoto, Taiki Yamaguchi, Takafumi Ishii, Takao Kudo, Takeshi Ibuka, Taku Watanabe, Tasuku Onodera, Toshiki Kataoka, Wenwen Li, Yoshihiro Yayama, Yusuke Asano","submitted_at":"2021-06-28T11:32:13Z","abstract_excerpt":"Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. To overcome this issue, we have developed a universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14583","kind":"arxiv","version":2},"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/2106.14583/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":"2106.14583","created_at":"2026-07-05T04:37:17.258370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14583v2","created_at":"2026-07-05T04:37:17.258370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14583","created_at":"2026-07-05T04:37:17.258370+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI76WFZ4VRVR","created_at":"2026-07-05T04:37:17.258370+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI76WFZ4VRVRRLMM","created_at":"2026-07-05T04:37:17.258370+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI76WFZ4","created_at":"2026-07-05T04:37:17.258370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05733","citing_title":"Density diversity in training data governs thermodynamic transferability of machine learning interatomic potentials","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7","json":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7.json","graph_json":"https://pith.science/api/pith-number/JI76WFZ4VRVRRLMMTYOIBEGTH7/graph.json","events_json":"https://pith.science/api/pith-number/JI76WFZ4VRVRRLMMTYOIBEGTH7/events.json","paper":"https://pith.science/paper/JI76WFZ4"},"agent_actions":{"view_html":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7","download_json":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7.json","view_paper":"https://pith.science/paper/JI76WFZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14583&json=true","fetch_graph":"https://pith.science/api/pith-number/JI76WFZ4VRVRRLMMTYOIBEGTH7/graph.json","fetch_events":"https://pith.science/api/pith-number/JI76WFZ4VRVRRLMMTYOIBEGTH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7/action/storage_attestation","attest_author":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7/action/author_attestation","sign_citation":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7/action/citation_signature","submit_replication":"https://pith.science/pith/JI76WFZ4VRVRRLMMTYOIBEGTH7/action/replication_record"}},"created_at":"2026-07-05T04:37:17.258370+00:00","updated_at":"2026-07-05T04:37:17.258370+00:00"}