{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XL5MQ33LWLNDAXO2JHL6M6W3QN","short_pith_number":"pith:XL5MQ33L","schema_version":"1.0","canonical_sha256":"bafac86f6bb2da305dda49d7e67adb8378439ee8ae3e1eecf5085184df22fab2","source":{"kind":"arxiv","id":"2406.14969","version":2},"attestation_state":"computed","paper":{"title":"Uni-Mol2: Exploring Molecular Pretraining Model at Scale","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guolin Ke, Hang Zheng, Linfeng Zhang, Weinan E, Xiaohong Ji, Zhen Wang, Zhifeng Gao","submitted_at":"2024-06-21T08:28:54Z","abstract_excerpt":"In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, gra"},"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":"2406.14969","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T08:28:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"66183e5c8fb2f76d1a8e0f14d7ef0309abd292d09f67130445efbc5cd0fad8d7","abstract_canon_sha256":"c6e755a2efd43ab7b3320d48d6646b2a618ead24cc5af756a835b69fc51a175b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:39.120884Z","signature_b64":"NOFuqqW6kyyKaSKenxtqy/Zat1JlDg9zNBN4+62SWJJ5t0CD03WAX0wwNlPJa0wqg0mb0HFQ/qgGYDwSxXKtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bafac86f6bb2da305dda49d7e67adb8378439ee8ae3e1eecf5085184df22fab2","last_reissued_at":"2026-07-05T08:38:39.120404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:39.120404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni-Mol2: Exploring Molecular Pretraining Model at Scale","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guolin Ke, Hang Zheng, Linfeng Zhang, Weinan E, Xiaohong Ji, Zhen Wang, Zhifeng Gao","submitted_at":"2024-06-21T08:28:54Z","abstract_excerpt":"In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14969","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.14969/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":"2406.14969","created_at":"2026-07-05T08:38:39.120464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14969v2","created_at":"2026-07-05T08:38:39.120464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14969","created_at":"2026-07-05T08:38:39.120464+00:00"},{"alias_kind":"pith_short_12","alias_value":"XL5MQ33LWLND","created_at":"2026-07-05T08:38:39.120464+00:00"},{"alias_kind":"pith_short_16","alias_value":"XL5MQ33LWLNDAXO2","created_at":"2026-07-05T08:38:39.120464+00:00"},{"alias_kind":"pith_short_8","alias_value":"XL5MQ33L","created_at":"2026-07-05T08:38:39.120464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22823","citing_title":"Retrieval-Augmented Multimodal Learning for Enzyme-Substrate Interaction Prediction Under Low-Homology Shift","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21002","citing_title":"A Unified Generative Framework for Scalable Chemical Reaction Network Exploration","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07656","citing_title":"SC3: The Multi-Solvent Solubility Challenge and Benchmark","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02419","citing_title":"DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution","ref_index":285,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19752","citing_title":"MSAlign: Aligning Molecule and Mass Spectra Foundation Models for Metabolite Identification","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02346","citing_title":"DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21942","citing_title":"Suiren-1.0 Technical Report: A Family of Molecular Foundation Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN","json":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN.json","graph_json":"https://pith.science/api/pith-number/XL5MQ33LWLNDAXO2JHL6M6W3QN/graph.json","events_json":"https://pith.science/api/pith-number/XL5MQ33LWLNDAXO2JHL6M6W3QN/events.json","paper":"https://pith.science/paper/XL5MQ33L"},"agent_actions":{"view_html":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN","download_json":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN.json","view_paper":"https://pith.science/paper/XL5MQ33L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14969&json=true","fetch_graph":"https://pith.science/api/pith-number/XL5MQ33LWLNDAXO2JHL6M6W3QN/graph.json","fetch_events":"https://pith.science/api/pith-number/XL5MQ33LWLNDAXO2JHL6M6W3QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN/action/storage_attestation","attest_author":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN/action/author_attestation","sign_citation":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN/action/citation_signature","submit_replication":"https://pith.science/pith/XL5MQ33LWLNDAXO2JHL6M6W3QN/action/replication_record"}},"created_at":"2026-07-05T08:38:39.120464+00:00","updated_at":"2026-07-05T08:38:39.120464+00:00"}