{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:55FOKKIMKH3BEVJGHBQ7XY5PPI","short_pith_number":"pith:55FOKKIM","schema_version":"1.0","canonical_sha256":"ef4ae5290c51f61255263861fbe3af7a1a357d8994488447702ed1216d0cb9ca","source":{"kind":"arxiv","id":"2310.14216","version":2},"attestation_state":"computed","paper":{"title":"UniMAP: Universal SMILES-Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Lixin Yang, Shikun Feng, Weiying Ma, Yanwen Huang, Yanyan Lan, Yuyan Ni","submitted_at":"2023-10-22T07:48:33Z","abstract_excerpt":"Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To effectively leverage both modalities, we argue that it is critical to capture the fine-grained 'semantics' between SMILES and graph, because subtle sequence/graph differences may lead to contrary molecular properties. In this paper, we propose a universal SMILE-graph representation learning model, namely UniMAP. Firstly, an embedding layer is employed to obtain the token and nod"},"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":"2310.14216","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T07:48:33Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"10a20ded282d272e436ec50e1687f520cc4277742014d367797df5e0caac806f","abstract_canon_sha256":"04c5d60ea3ab545ec68e751f3ceb0a449246483e79a3a4584e5172b93073c2a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:04.781086Z","signature_b64":"y/PTLo7nQaOalwTEguy4u/BGr08OUaX6ooBnEvUVHN12aIn77JwzS5b6B9y38U6NtqxDHMlJLuFatPRHSarxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef4ae5290c51f61255263861fbe3af7a1a357d8994488447702ed1216d0cb9ca","last_reissued_at":"2026-07-05T09:30:04.780647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:04.780647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMAP: Universal SMILES-Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Lixin Yang, Shikun Feng, Weiying Ma, Yanwen Huang, Yanyan Lan, Yuyan Ni","submitted_at":"2023-10-22T07:48:33Z","abstract_excerpt":"Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To effectively leverage both modalities, we argue that it is critical to capture the fine-grained 'semantics' between SMILES and graph, because subtle sequence/graph differences may lead to contrary molecular properties. In this paper, we propose a universal SMILE-graph representation learning model, namely UniMAP. Firstly, an embedding layer is employed to obtain the token and nod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14216","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/2310.14216/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":"2310.14216","created_at":"2026-07-05T09:30:04.780700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14216v2","created_at":"2026-07-05T09:30:04.780700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14216","created_at":"2026-07-05T09:30:04.780700+00:00"},{"alias_kind":"pith_short_12","alias_value":"55FOKKIMKH3B","created_at":"2026-07-05T09:30:04.780700+00:00"},{"alias_kind":"pith_short_16","alias_value":"55FOKKIMKH3BEVJG","created_at":"2026-07-05T09:30:04.780700+00:00"},{"alias_kind":"pith_short_8","alias_value":"55FOKKIM","created_at":"2026-07-05T09:30:04.780700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05427","citing_title":"Large Language Models Transform Organic Synthesis From Reaction Prediction to Automation","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI","json":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI.json","graph_json":"https://pith.science/api/pith-number/55FOKKIMKH3BEVJGHBQ7XY5PPI/graph.json","events_json":"https://pith.science/api/pith-number/55FOKKIMKH3BEVJGHBQ7XY5PPI/events.json","paper":"https://pith.science/paper/55FOKKIM"},"agent_actions":{"view_html":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI","download_json":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI.json","view_paper":"https://pith.science/paper/55FOKKIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14216&json=true","fetch_graph":"https://pith.science/api/pith-number/55FOKKIMKH3BEVJGHBQ7XY5PPI/graph.json","fetch_events":"https://pith.science/api/pith-number/55FOKKIMKH3BEVJGHBQ7XY5PPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/action/storage_attestation","attest_author":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/action/author_attestation","sign_citation":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/action/citation_signature","submit_replication":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/action/replication_record"}},"created_at":"2026-07-05T09:30:04.780700+00:00","updated_at":"2026-07-05T09:30:04.780700+00:00"}