{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DFCJHKFD24BX6TCNNSNDUILFBL","short_pith_number":"pith:DFCJHKFD","schema_version":"1.0","canonical_sha256":"194493a8a3d7037f4c4d6c9a3a21650ad777ebaea0679ec8026a5e8e297ff3ec","source":{"kind":"arxiv","id":"1901.02717","version":2},"attestation_state":"computed","paper":{"title":"Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","stat.ML"],"primary_cat":"physics.comp-ph","authors_text":"Anna Hiszpanski, Bhavya Kailkhura, Brian Gallagher, Sookyung Kim, T. Yong-Jin Han","submitted_at":"2019-01-05T02:17:57Z","abstract_excerpt":"Material scientists are increasingly adopting the use of machine learning (ML) for making potentially important decisions, such as, discovery, development, optimization, synthesis and characterization of materials. However, despite ML's impressive performance in commercial applications, several unique challenges exist when applying ML in materials science applications. In such a context, the contributions of this work are twofold. First, we identify common pitfalls of existing ML techniques when learning from underrepresented/imbalanced material data. Specifically, we show that with imbalanced"},"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":"1901.02717","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2019-01-05T02:17:57Z","cross_cats_sorted":["cond-mat.mtrl-sci","stat.ML"],"title_canon_sha256":"9e43ab579074c5b0993c6f5aced6ce16da6cf37dc6485e5769597be7e8b4c24f","abstract_canon_sha256":"e341c6ff6b8120067186bbfb75d8fb33c25a5027f623d064cbece2b63c1edf86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:41.828693Z","signature_b64":"cJEn8ebc0K5+VA2R9s5fjUi9BE6UVHB3rs2hcy640/YLyHe4vGkwYLEWcjHM1xX5oGUq4FuN9ORFaLVkTe37DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"194493a8a3d7037f4c4d6c9a3a21650ad777ebaea0679ec8026a5e8e297ff3ec","last_reissued_at":"2026-05-17T23:51:41.828259Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:41.828259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","stat.ML"],"primary_cat":"physics.comp-ph","authors_text":"Anna Hiszpanski, Bhavya Kailkhura, Brian Gallagher, Sookyung Kim, T. Yong-Jin Han","submitted_at":"2019-01-05T02:17:57Z","abstract_excerpt":"Material scientists are increasingly adopting the use of machine learning (ML) for making potentially important decisions, such as, discovery, development, optimization, synthesis and characterization of materials. However, despite ML's impressive performance in commercial applications, several unique challenges exist when applying ML in materials science applications. In such a context, the contributions of this work are twofold. First, we identify common pitfalls of existing ML techniques when learning from underrepresented/imbalanced material data. Specifically, we show that with imbalanced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02717","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":""},"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":"1901.02717","created_at":"2026-05-17T23:51:41.828327+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02717v2","created_at":"2026-05-17T23:51:41.828327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02717","created_at":"2026-05-17T23:51:41.828327+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFCJHKFD24BX","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFCJHKFD24BX6TCN","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFCJHKFD","created_at":"2026-05-18T12:33:15.570797+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/DFCJHKFD24BX6TCNNSNDUILFBL","json":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL.json","graph_json":"https://pith.science/api/pith-number/DFCJHKFD24BX6TCNNSNDUILFBL/graph.json","events_json":"https://pith.science/api/pith-number/DFCJHKFD24BX6TCNNSNDUILFBL/events.json","paper":"https://pith.science/paper/DFCJHKFD"},"agent_actions":{"view_html":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL","download_json":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL.json","view_paper":"https://pith.science/paper/DFCJHKFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02717&json=true","fetch_graph":"https://pith.science/api/pith-number/DFCJHKFD24BX6TCNNSNDUILFBL/graph.json","fetch_events":"https://pith.science/api/pith-number/DFCJHKFD24BX6TCNNSNDUILFBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL/action/storage_attestation","attest_author":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL/action/author_attestation","sign_citation":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL/action/citation_signature","submit_replication":"https://pith.science/pith/DFCJHKFD24BX6TCNNSNDUILFBL/action/replication_record"}},"created_at":"2026-05-17T23:51:41.828327+00:00","updated_at":"2026-05-17T23:51:41.828327+00:00"}