{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6DTRR7U7DERLHHHDRBXU4KI6JS","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":"202e78e0302832d348ee1bc678ad6f07a7c2add10c55690d6376858506a13093","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T15:15:24Z","title_canon_sha256":"7fe1690243b5d20506000e0fa0baeab3632e0cb99edcdd902f49ae26f47df61a"},"schema_version":"1.0","source":{"id":"2411.10821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10821","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10821v1","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10821","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"6DTRR7U7DERL","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_16","alias_value":"6DTRR7U7DERLHHHD","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_8","alias_value":"6DTRR7U7","created_at":"2026-07-05T09:36:51Z"}],"graph_snapshots":[{"event_id":"sha256:5042fdfc3a1012b1eb116f2401d8422043b1f34331943aed7d29c49488e680b0","target":"graph","created_at":"2026-07-05T09:36:51Z","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/2411.10821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining molecular representations is crucial for drug and material discovery. Recent methods focus on learning representations from geometric structures, effectively capturing 3D position information. Yet, they overlook the rich information in biomedical texts, which detail molecules' properties and substructures. With this in mind, we set up a data collection effort for 200K pairs of ground-state geometric structures and biomedical texts, resulting in a PubChem3D dataset. Based on this dataset, we propose the GeomCLIP framework to enhance for multi-modal representation learning from molec","authors_text":"Chao Cui, Huaisheng Zhu, Teng Xiao, Vasant G. Honavar","cross_cats":["q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T15:15:24Z","title":"GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10821","kind":"arxiv","version":1},"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":"sha256:7ebb455e4ba400b154c9fb960020e6573fff4bb589d0b1c069d08c0f16a13ce7","target":"record","created_at":"2026-07-05T09:36:51Z","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":"202e78e0302832d348ee1bc678ad6f07a7c2add10c55690d6376858506a13093","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T15:15:24Z","title_canon_sha256":"7fe1690243b5d20506000e0fa0baeab3632e0cb99edcdd902f49ae26f47df61a"},"schema_version":"1.0","source":{"id":"2411.10821","kind":"arxiv","version":1}},"canonical_sha256":"f0e718fe9f1922b39ce3886f4e291e4cbbbaf25dd7c8041dacbb6fb2448fc71f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0e718fe9f1922b39ce3886f4e291e4cbbbaf25dd7c8041dacbb6fb2448fc71f","first_computed_at":"2026-07-05T09:36:51.805385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:51.805385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vdh7zvOsn+tOf9gkOf/RJS1jPOW8QGxXvWdEnlk2T4Pr8E0x5OjU14N8Aizhm49DbIBpNd+sHevjtJ+f5QKeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:51.805922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ebb455e4ba400b154c9fb960020e6573fff4bb589d0b1c069d08c0f16a13ce7","sha256:5042fdfc3a1012b1eb116f2401d8422043b1f34331943aed7d29c49488e680b0"],"state_sha256":"28620661ecd4abd5ab9b79484d2c8a4362ce8fe1c32fe4e8342b5a70de946df1"}