{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJKTV247QMWZ3PDI4YPZQZ3WXE","short_pith_number":"pith:BJKTV247","schema_version":"1.0","canonical_sha256":"0a553aeb9f832d9dbc68e61f986776b920d58985066631c1788481d38b6c3676","source":{"kind":"arxiv","id":"2403.12995","version":4},"attestation_state":"computed","paper":{"title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CE","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Hao Zhou, Junwei Yang, Kangjie Zheng (equal contribution), Ming Zhang, Siyu Long (equal contribution), Tianyu Lu, Wei-Ying Ma, Xinyu Dai, Zaiqing Nie","submitted_at":"2024-03-05T13:35:41Z","abstract_excerpt":"Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pre-training on multi-scale code-"},"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":"2403.12995","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-03-05T13:35:41Z","cross_cats_sorted":["cs.CE","cs.LG"],"title_canon_sha256":"a17bc70455794fde818c4b81e88e6477f7dec9e63652dd9690478e7c32213e0d","abstract_canon_sha256":"e67f3da85340c12a5e9f98909057d6e153987c54c5b5d6b128d8627ad2d1b45f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:13.175143Z","signature_b64":"0dtt2sRmPAqDrZu/aQKgXi55Ra+qjNgQBe6oZkGvQH8RCF4Ye6OZ6AIYzOWNNWfRWPa3fGM0TWf2I8iQi2m5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a553aeb9f832d9dbc68e61f986776b920d58985066631c1788481d38b6c3676","last_reissued_at":"2026-07-05T08:31:13.174607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:13.174607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CE","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Hao Zhou, Junwei Yang, Kangjie Zheng (equal contribution), Ming Zhang, Siyu Long (equal contribution), Tianyu Lu, Wei-Ying Ma, Xinyu Dai, Zaiqing Nie","submitted_at":"2024-03-05T13:35:41Z","abstract_excerpt":"Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pre-training on multi-scale code-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12995","kind":"arxiv","version":4},"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/2403.12995/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":"2403.12995","created_at":"2026-07-05T08:31:13.174666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12995v4","created_at":"2026-07-05T08:31:13.174666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12995","created_at":"2026-07-05T08:31:13.174666+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJKTV247QMWZ","created_at":"2026-07-05T08:31:13.174666+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJKTV247QMWZ3PDI","created_at":"2026-07-05T08:31:13.174666+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJKTV247","created_at":"2026-07-05T08:31:13.174666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08293","citing_title":"Diffusion Sequence Models for Enhanced Protein Representation and Generation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE","json":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE.json","graph_json":"https://pith.science/api/pith-number/BJKTV247QMWZ3PDI4YPZQZ3WXE/graph.json","events_json":"https://pith.science/api/pith-number/BJKTV247QMWZ3PDI4YPZQZ3WXE/events.json","paper":"https://pith.science/paper/BJKTV247"},"agent_actions":{"view_html":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE","download_json":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE.json","view_paper":"https://pith.science/paper/BJKTV247","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12995&json=true","fetch_graph":"https://pith.science/api/pith-number/BJKTV247QMWZ3PDI4YPZQZ3WXE/graph.json","fetch_events":"https://pith.science/api/pith-number/BJKTV247QMWZ3PDI4YPZQZ3WXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE/action/storage_attestation","attest_author":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE/action/author_attestation","sign_citation":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE/action/citation_signature","submit_replication":"https://pith.science/pith/BJKTV247QMWZ3PDI4YPZQZ3WXE/action/replication_record"}},"created_at":"2026-07-05T08:31:13.174666+00:00","updated_at":"2026-07-05T08:31:13.174666+00:00"}