{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:55FOKKIMKH3BEVJGHBQ7XY5PPI","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":"04c5d60ea3ab545ec68e751f3ceb0a449246483e79a3a4584e5172b93073c2a4","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T07:48:33Z","title_canon_sha256":"10a20ded282d272e436ec50e1687f520cc4277742014d367797df5e0caac806f"},"schema_version":"1.0","source":{"id":"2310.14216","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14216","created_at":"2026-07-05T09:30:04Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14216v2","created_at":"2026-07-05T09:30:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14216","created_at":"2026-07-05T09:30:04Z"},{"alias_kind":"pith_short_12","alias_value":"55FOKKIMKH3B","created_at":"2026-07-05T09:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"55FOKKIMKH3BEVJG","created_at":"2026-07-05T09:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"55FOKKIM","created_at":"2026-07-05T09:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:ba39261211991969ff240877c8b1e42592c42afc0b029e565ad3c56a358ba7bf","target":"graph","created_at":"2026-07-05T09:30:04Z","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/2310.14216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lixin Yang, Shikun Feng, Weiying Ma, Yanwen Huang, Yanyan Lan, Yuyan Ni","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T07:48:33Z","title":"UniMAP: Universal SMILES-Graph Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14216","kind":"arxiv","version":2},"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":"sha256:8d10b5955ea8b9f40444d418cee6fdf3e4f317762097f421eba6ff03e06996ab","target":"record","created_at":"2026-07-05T09:30:04Z","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":"04c5d60ea3ab545ec68e751f3ceb0a449246483e79a3a4584e5172b93073c2a4","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T07:48:33Z","title_canon_sha256":"10a20ded282d272e436ec50e1687f520cc4277742014d367797df5e0caac806f"},"schema_version":"1.0","source":{"id":"2310.14216","kind":"arxiv","version":2}},"canonical_sha256":"ef4ae5290c51f61255263861fbe3af7a1a357d8994488447702ed1216d0cb9ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef4ae5290c51f61255263861fbe3af7a1a357d8994488447702ed1216d0cb9ca","first_computed_at":"2026-07-05T09:30:04.780647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:04.780647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y/PTLo7nQaOalwTEguy4u/BGr08OUaX6ooBnEvUVHN12aIn77JwzS5b6B9y38U6NtqxDHMlJLuFatPRHSarxBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:04.781086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14216","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d10b5955ea8b9f40444d418cee6fdf3e4f317762097f421eba6ff03e06996ab","sha256:ba39261211991969ff240877c8b1e42592c42afc0b029e565ad3c56a358ba7bf"],"state_sha256":"e17f734c870e814781336ddee246072f4cf47826438eaf74f189998d4e024392"}