{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VEPBV227T2GG7QLBTZVSLMZXBW","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":"e5f7dbfe944aeeac32d5387a8ce13c873a189177f22fb4cc37fdba0e3020f3c8","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-11-15T04:12:00Z","title_canon_sha256":"f5377e777440c71ee5527f461c2350458a5b6bb691d93c3551af4c1b6dbb46a1"},"schema_version":"1.0","source":{"id":"2211.07881","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07881","created_at":"2026-07-05T05:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07881v4","created_at":"2026-07-05T05:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07881","created_at":"2026-07-05T05:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"VEPBV227T2GG","created_at":"2026-07-05T05:59:41Z"},{"alias_kind":"pith_short_16","alias_value":"VEPBV227T2GG7QLB","created_at":"2026-07-05T05:59:41Z"},{"alias_kind":"pith_short_8","alias_value":"VEPBV227","created_at":"2026-07-05T05:59:41Z"}],"graph_snapshots":[{"event_id":"sha256:3b57cb8978d3e65625499fe551c03472d3933c63a40f499b4d367e1b08dd0284","target":"graph","created_at":"2026-07-05T05:59:41Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.07881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Growing materials data and data-driven informatics drastically promote the discovery and design of materials. While there are significant advancements in data-driven models, the quality of data resources is less studied despite its huge impact on model performance. In this work, we focus on data bias arising from uneven coverage of materials families in existing knowledge. Observing different diversities among crystal systems in common materials databases, we propose an information entropy-based metric for measuring this bias. To mitigate the bias, we develop an entropy-targeted active learnin","authors_text":"Hengrui Zhang, James M. Rondinelli, Wei Chen, Wei Wayne Chen","cross_cats":["cs.DB","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-11-15T04:12:00Z","title":"ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07881","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2872db25553f8ea414c10886460490291ca2c50b727cf7fbae46cda29cdb679","target":"record","created_at":"2026-07-05T05:59:41Z","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":"e5f7dbfe944aeeac32d5387a8ce13c873a189177f22fb4cc37fdba0e3020f3c8","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-11-15T04:12:00Z","title_canon_sha256":"f5377e777440c71ee5527f461c2350458a5b6bb691d93c3551af4c1b6dbb46a1"},"schema_version":"1.0","source":{"id":"2211.07881","kind":"arxiv","version":4}},"canonical_sha256":"a91e1aeb5f9e8c6fc1619e6b25b3370d93150975ed7390ac275736e78f850e54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a91e1aeb5f9e8c6fc1619e6b25b3370d93150975ed7390ac275736e78f850e54","first_computed_at":"2026-07-05T05:59:41.581372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:41.581372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wEwjsdBNxpl9mCZdsVYqHT7s12Km6N086VVHz903UDmlIqHjm7nhmNK8VyIgWvrCOAV1hb5FKp2uh/PwfLN/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:41.581872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07881","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2872db25553f8ea414c10886460490291ca2c50b727cf7fbae46cda29cdb679","sha256:3b57cb8978d3e65625499fe551c03472d3933c63a40f499b4d367e1b08dd0284"],"state_sha256":"7db8d187e86f6aab4a6ad8b1ed341b55b44f10dd0a281f934b0f1d28a9bce3ec"}