{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HD7LB2TSQVWESZSI3UYHKMUKHU","short_pith_number":"pith:HD7LB2TS","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"},"canonical_sha256":"38feb0ea72856c496648dd3075328a3d01cdc73c981b8aae469581d6df74bc57","source":{"kind":"arxiv","id":"2408.06150","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06150","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06150v3","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06150","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"pith_short_12","alias_value":"HD7LB2TSQVWE","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"pith_short_16","alias_value":"HD7LB2TSQVWESZSI","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"pith_short_8","alias_value":"HD7LB2TS","created_at":"2026-07-05T10:57:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HD7LB2TSQVWESZSI3UYHKMUKHU","target":"record","payload":{"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"},"canonical_sha256":"38feb0ea72856c496648dd3075328a3d01cdc73c981b8aae469581d6df74bc57","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"},"source_kind":"arxiv","source_id":"2408.06150","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/761wVYJen8FAFa6ap3dKjY/LXBzBKSas38jiDtRVnDWVC58JEdb/7WXehrGe0NzLlcA/9MtI92crKnXnbjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:34:18.278176Z"},"content_sha256":"b61c212a0a14d3b1bc01d7710a9614583d0f6e40d50e99353b11fc8c08e84a98","schema_version":"1.0","event_id":"sha256:b61c212a0a14d3b1bc01d7710a9614583d0f6e40d50e99353b11fc8c08e84a98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HD7LB2TSQVWESZSI3UYHKMUKHU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPAg8JyNMlkZtm44k0lu90BdxJ54Wg0x6DKOovejQqf6iGqW8K9Ug7eaFz4t/n01fje3l33KrkFqNfvMKrhMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:34:18.279081Z"},"content_sha256":"1372f96793befebb8c1442f23dfa6deb3084abd57d06ad7eb9a85f43312f57f6","schema_version":"1.0","event_id":"sha256:1372f96793befebb8c1442f23dfa6deb3084abd57d06ad7eb9a85f43312f57f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/bundle.json","state_url":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T16:34:18Z","links":{"resolver":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU","bundle":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/bundle.json","state":"https://pith.science/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HD7LB2TSQVWESZSI3UYHKMUKHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HD7LB2TSQVWESZSI3UYHKMUKHU","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":"d70f65631e7d9568e2f28527b7e69acf0ee6ddf82b9a451b9144e505b2a630f1","cross_cats_sorted":["physics.chem-ph","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T13:44:24Z","title_canon_sha256":"da5e0585e94f0b9634a5b9afd8fbc8ce1f0a89815412aba1599f0e4c1372b216"},"schema_version":"1.0","source":{"id":"2408.06150","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06150","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06150v3","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06150","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"pith_short_12","alias_value":"HD7LB2TSQVWE","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"pith_short_16","alias_value":"HD7LB2TSQVWESZSI","created_at":"2026-07-05T10:57:53Z"},{"alias_kind":"pith_short_8","alias_value":"HD7LB2TS","created_at":"2026-07-05T10:57:53Z"}],"graph_snapshots":[{"event_id":"sha256:1372f96793befebb8c1442f23dfa6deb3084abd57d06ad7eb9a85f43312f57f6","target":"graph","created_at":"2026-07-05T10:57:53Z","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/2408.06150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["physics.chem-ph","q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T13:44:24Z","title":"LipidBERT: A Lipid Language Model Pre-trained on METiS de novo Lipid Library"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06150","kind":"arxiv","version":3},"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:b61c212a0a14d3b1bc01d7710a9614583d0f6e40d50e99353b11fc8c08e84a98","target":"record","created_at":"2026-07-05T10:57:53Z","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":"d70f65631e7d9568e2f28527b7e69acf0ee6ddf82b9a451b9144e505b2a630f1","cross_cats_sorted":["physics.chem-ph","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T13:44:24Z","title_canon_sha256":"da5e0585e94f0b9634a5b9afd8fbc8ce1f0a89815412aba1599f0e4c1372b216"},"schema_version":"1.0","source":{"id":"2408.06150","kind":"arxiv","version":3}},"canonical_sha256":"38feb0ea72856c496648dd3075328a3d01cdc73c981b8aae469581d6df74bc57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38feb0ea72856c496648dd3075328a3d01cdc73c981b8aae469581d6df74bc57","first_computed_at":"2026-07-05T10:57:53.332420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:53.332420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V9PP+4IF923C6pdSXe25KwwkmM8K+ZJa/IKaahYogJ07xh0u3JFXO3GNMOEO/R79Kv9cA1OIxtaLyZnhaDKWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:53.332913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06150","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b61c212a0a14d3b1bc01d7710a9614583d0f6e40d50e99353b11fc8c08e84a98","sha256:1372f96793befebb8c1442f23dfa6deb3084abd57d06ad7eb9a85f43312f57f6"],"state_sha256":"a1f5a98a8b85a312bdc437a267a284f39aedc8acc1e0fd27c63d13c53b44c858"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g98EMdp08fCtEG/En1voKJBXTG8rBgigNNULo4pXmwMoognGpN3VWBvCWluwaWUazGwXo12+itFeTWPeVSowAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:34:18.284891Z","bundle_sha256":"9b9f643cd294a187a2828f59f7d1d9d15c67273a682ee33b618e9c7d90c5a478"}}