{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:55FOKKIMKH3BEVJGHBQ7XY5PPI","short_pith_number":"pith:55FOKKIM","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"},"canonical_sha256":"ef4ae5290c51f61255263861fbe3af7a1a357d8994488447702ed1216d0cb9ca","source":{"kind":"arxiv","id":"2310.14216","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:55FOKKIMKH3BEVJGHBQ7XY5PPI","target":"record","payload":{"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"},"canonical_sha256":"ef4ae5290c51f61255263861fbe3af7a1a357d8994488447702ed1216d0cb9ca","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"},"source_kind":"arxiv","source_id":"2310.14216","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g7Q6REZMM3VoFd1shhcGgi+fa67a4Qv+U2aNg+7twUTaw7UIUzv3FHvbrhw9bwQx8vDjJHbxS+bucMpuT2kaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:17:49.825735Z"},"content_sha256":"8d10b5955ea8b9f40444d418cee6fdf3e4f317762097f421eba6ff03e06996ab","schema_version":"1.0","event_id":"sha256:8d10b5955ea8b9f40444d418cee6fdf3e4f317762097f421eba6ff03e06996ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:55FOKKIMKH3BEVJGHBQ7XY5PPI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjb0QkwMsZmbPjeLfIGKuIXAKYOYRucCcVe0tFvUQLH7NWml9ALWkmKJ05Z9WM1nLVNC43624vaDJn1iNetZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:17:49.826294Z"},"content_sha256":"ba39261211991969ff240877c8b1e42592c42afc0b029e565ad3c56a358ba7bf","schema_version":"1.0","event_id":"sha256:ba39261211991969ff240877c8b1e42592c42afc0b029e565ad3c56a358ba7bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/bundle.json","state_url":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T10:17:49Z","links":{"resolver":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI","bundle":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/bundle.json","state":"https://pith.science/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55FOKKIMKH3BEVJGHBQ7XY5PPI/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b2xFI4eUu2U+N5JZ/QJkeeTtcLEatDECTDbPkZQVSyQnA8c+UP7I1bYOO3oegWT1lEzpLjob4hwXP/f7yuG1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T10:17:49.831178Z","bundle_sha256":"5065659badf9785bbadccf401bc6852cd25d39e58861568992dd9c0c5f24a084"}}