{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HD7LB2TSQVWESZSI3UYHKMUKHU","short_pith_number":"pith:HD7LB2TS","schema_version":"1.0","canonical_sha256":"38feb0ea72856c496648dd3075328a3d01cdc73c981b8aae469581d6df74bc57","source":{"kind":"arxiv","id":"2408.06150","version":3},"attestation_state":"computed","paper":{"title":"LipidBERT: A Lipid Language Model Pre-trained on METiS de novo Lipid Library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Andong Liu, Cai Yao, Chris Lai, Feng Shi, Jiali Zou, Kai Wang, Kangjie Lyu, Lin Zhang, Tianhao Yu, Wenshou Wang, Xicheng Zhang, Xuan Bai, Zhuorui Sun","submitted_at":"2024-08-12T13:44:24Z","abstract_excerpt":"In this study, we generate and maintain a database of 10 million virtual lipids through METiS's in-house de novo lipid generation algorithms and lipid virtual screening techniques. These virtual lipids serve as a corpus for pre-training, lipid representation learning, and downstream task knowledge transfer, culminating in state-of-the-art LNP property prediction performance. We propose LipidBERT, a BERT-like model pre-trained with the Masked Language Model (MLM) and various secondary tasks. Additionally, we compare the performance of embeddings generated by LipidBERT and PhatGPT, our GPT-like "},"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":"2408.06150","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T13:44:24Z","cross_cats_sorted":["physics.chem-ph","q-bio.BM"],"title_canon_sha256":"da5e0585e94f0b9634a5b9afd8fbc8ce1f0a89815412aba1599f0e4c1372b216","abstract_canon_sha256":"d70f65631e7d9568e2f28527b7e69acf0ee6ddf82b9a451b9144e505b2a630f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:53.332913Z","signature_b64":"V9PP+4IF923C6pdSXe25KwwkmM8K+ZJa/IKaahYogJ07xh0u3JFXO3GNMOEO/R79Kv9cA1OIxtaLyZnhaDKWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38feb0ea72856c496648dd3075328a3d01cdc73c981b8aae469581d6df74bc57","last_reissued_at":"2026-07-05T10:57:53.332420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:53.332420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LipidBERT: A Lipid Language Model Pre-trained on METiS de novo Lipid Library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Andong Liu, Cai Yao, Chris Lai, Feng Shi, Jiali Zou, Kai Wang, Kangjie Lyu, Lin Zhang, Tianhao Yu, Wenshou Wang, Xicheng Zhang, Xuan Bai, Zhuorui Sun","submitted_at":"2024-08-12T13:44:24Z","abstract_excerpt":"In this study, we generate and maintain a database of 10 million virtual lipids through METiS's in-house de novo lipid generation algorithms and lipid virtual screening techniques. These virtual lipids serve as a corpus for pre-training, lipid representation learning, and downstream task knowledge transfer, culminating in state-of-the-art LNP property prediction performance. We propose LipidBERT, a BERT-like model pre-trained with the Masked Language Model (MLM) and various secondary tasks. Additionally, we compare the performance of embeddings generated by LipidBERT and PhatGPT, our GPT-like "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06150","kind":"arxiv","version":3},"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/2408.06150/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":"2408.06150","created_at":"2026-07-05T10:57:53.332477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06150v3","created_at":"2026-07-05T10:57:53.332477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06150","created_at":"2026-07-05T10:57:53.332477+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD7LB2TSQVWE","created_at":"2026-07-05T10:57:53.332477+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD7LB2TSQVWESZSI","created_at":"2026-07-05T10:57:53.332477+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD7LB2TS","created_at":"2026-07-05T10:57:53.332477+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/HD7LB2TSQVWESZSI3UYHKMUKHU","json":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU.json","graph_json":"https://pith.science/api/pith-number/HD7LB2TSQVWESZSI3UYHKMUKHU/graph.json","events_json":"https://pith.science/api/pith-number/HD7LB2TSQVWESZSI3UYHKMUKHU/events.json","paper":"https://pith.science/paper/HD7LB2TS"},"agent_actions":{"view_html":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU","download_json":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU.json","view_paper":"https://pith.science/paper/HD7LB2TS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06150&json=true","fetch_graph":"https://pith.science/api/pith-number/HD7LB2TSQVWESZSI3UYHKMUKHU/graph.json","fetch_events":"https://pith.science/api/pith-number/HD7LB2TSQVWESZSI3UYHKMUKHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/action/storage_attestation","attest_author":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/action/author_attestation","sign_citation":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/action/citation_signature","submit_replication":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/action/replication_record"}},"created_at":"2026-07-05T10:57:53.332477+00:00","updated_at":"2026-07-05T10:57:53.332477+00:00"}