{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2DPT4IAF336AVZBABXXDTDB4XZ","short_pith_number":"pith:2DPT4IAF","schema_version":"1.0","canonical_sha256":"d0df3e2005defc0ae4200dee398c3cbe555935cf87f1ff1c21d548a6aa59ef8e","source":{"kind":"arxiv","id":"2012.11175","version":1},"attestation_state":"computed","paper":{"title":"Learn molecular representations from large-scale unlabeled molecules for drug discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Guotong Xie, Hao Chen, Jun Wang, Peng Gao, Pengyong Li, Sen Song, Xiaojun Yao, Yihuan Yu, Yixuan Qiao","submitted_at":"2020-12-21T08:21:49Z","abstract_excerpt":"How to produce expressive molecular representations is a fundamental challenge in AI-driven drug discovery. Graph neural network (GNN) has emerged as a powerful technique for modeling molecular data. However, previous supervised approaches usually suffer from the scarcity of labeled data and have poor generalization capability. Here, we proposed a novel Molecular Pre-training Graph-based deep learning framework, named MPG, that leans molecular representations from large-scale unlabeled molecules. In MPG, we proposed a powerful MolGNet model and an effective self-supervised strategy for pre-tra"},"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":"2012.11175","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T08:21:49Z","cross_cats_sorted":["q-bio.BM","q-bio.QM"],"title_canon_sha256":"882f4c698b23f2cd2a7c7458b5d24428daa4fc56083bb870c9fada413e382204","abstract_canon_sha256":"b02441ce64b695a1f350af9ce56b41c513dc2bc8d44d681912f638123fbfa8ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:59.552089Z","signature_b64":"pQFO4y/f7nt1vDng33x+8WDnBYIwYcGAYmWwd8ohH1iyyQxvNegeEim9ffMozXmZdgV9OCL5jfbBZ8GRcClnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0df3e2005defc0ae4200dee398c3cbe555935cf87f1ff1c21d548a6aa59ef8e","last_reissued_at":"2026-07-05T02:00:59.551686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:59.551686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn molecular representations from large-scale unlabeled molecules for drug discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Guotong Xie, Hao Chen, Jun Wang, Peng Gao, Pengyong Li, Sen Song, Xiaojun Yao, Yihuan Yu, Yixuan Qiao","submitted_at":"2020-12-21T08:21:49Z","abstract_excerpt":"How to produce expressive molecular representations is a fundamental challenge in AI-driven drug discovery. Graph neural network (GNN) has emerged as a powerful technique for modeling molecular data. However, previous supervised approaches usually suffer from the scarcity of labeled data and have poor generalization capability. Here, we proposed a novel Molecular Pre-training Graph-based deep learning framework, named MPG, that leans molecular representations from large-scale unlabeled molecules. In MPG, we proposed a powerful MolGNet model and an effective self-supervised strategy for pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11175","kind":"arxiv","version":1},"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/2012.11175/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":"2012.11175","created_at":"2026-07-05T02:00:59.551738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11175v1","created_at":"2026-07-05T02:00:59.551738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11175","created_at":"2026-07-05T02:00:59.551738+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DPT4IAF336A","created_at":"2026-07-05T02:00:59.551738+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DPT4IAF336AVZBA","created_at":"2026-07-05T02:00:59.551738+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DPT4IAF","created_at":"2026-07-05T02:00:59.551738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06336","citing_title":"BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ","json":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ.json","graph_json":"https://pith.science/api/pith-number/2DPT4IAF336AVZBABXXDTDB4XZ/graph.json","events_json":"https://pith.science/api/pith-number/2DPT4IAF336AVZBABXXDTDB4XZ/events.json","paper":"https://pith.science/paper/2DPT4IAF"},"agent_actions":{"view_html":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ","download_json":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ.json","view_paper":"https://pith.science/paper/2DPT4IAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11175&json=true","fetch_graph":"https://pith.science/api/pith-number/2DPT4IAF336AVZBABXXDTDB4XZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2DPT4IAF336AVZBABXXDTDB4XZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ/action/storage_attestation","attest_author":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ/action/author_attestation","sign_citation":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ/action/citation_signature","submit_replication":"https://pith.science/pith/2DPT4IAF336AVZBABXXDTDB4XZ/action/replication_record"}},"created_at":"2026-07-05T02:00:59.551738+00:00","updated_at":"2026-07-05T02:00:59.551738+00:00"}