{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XAS53CSWA3IASZEQE737A6DVXH","short_pith_number":"pith:XAS53CSW","schema_version":"1.0","canonical_sha256":"b825dd8a5606d009649027f7f07875b9ebcc5735fc7cf4bae95dd9b48c838109","source":{"kind":"arxiv","id":"2405.17829","version":4},"attestation_state":"computed","paper":{"title":"LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinho Chang, Jong Chul Ye","submitted_at":"2024-05-28T04:59:13Z","abstract_excerpt":"With the emergence of diffusion models as a frontline generative model, many researchers have proposed molecule generation techniques with conditional diffusion models. However, the unavoidable discreteness of a molecule makes it difficult for a diffusion model to connect raw data with highly complex conditions like natural language. To address this, here we present a novel latent diffusion model dubbed LDMol for text-conditioned molecule generation. By recognizing that the suitable latent space design is the key to the diffusion model performance, we employ a contrastive learning strategy to "},"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":"2405.17829","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T04:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"952e001af667aba2ea8ec2cdac3f5c95a000893132663b0378c42e70db4db0ca","abstract_canon_sha256":"a6ef3864b1f9026fb98f463d9a5d9be64814e0c4663976be2d33317398b74d5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:17.037274Z","signature_b64":"SzR3KVcqT1yriN5iuH+W+HJnre7GmXVkO6vgx1rz6fXny5NV2qlufQBK+xGiqgLqF/ZFb4fK2l1CBTzALk/wBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b825dd8a5606d009649027f7f07875b9ebcc5735fc7cf4bae95dd9b48c838109","last_reissued_at":"2026-07-05T11:15:17.036805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:17.036805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinho Chang, Jong Chul Ye","submitted_at":"2024-05-28T04:59:13Z","abstract_excerpt":"With the emergence of diffusion models as a frontline generative model, many researchers have proposed molecule generation techniques with conditional diffusion models. However, the unavoidable discreteness of a molecule makes it difficult for a diffusion model to connect raw data with highly complex conditions like natural language. To address this, here we present a novel latent diffusion model dubbed LDMol for text-conditioned molecule generation. By recognizing that the suitable latent space design is the key to the diffusion model performance, we employ a contrastive learning strategy to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17829","kind":"arxiv","version":4},"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/2405.17829/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":"2405.17829","created_at":"2026-07-05T11:15:17.036862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17829v4","created_at":"2026-07-05T11:15:17.036862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17829","created_at":"2026-07-05T11:15:17.036862+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAS53CSWA3IA","created_at":"2026-07-05T11:15:17.036862+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAS53CSWA3IASZEQ","created_at":"2026-07-05T11:15:17.036862+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAS53CSW","created_at":"2026-07-05T11:15:17.036862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22287","citing_title":"SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH","json":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH.json","graph_json":"https://pith.science/api/pith-number/XAS53CSWA3IASZEQE737A6DVXH/graph.json","events_json":"https://pith.science/api/pith-number/XAS53CSWA3IASZEQE737A6DVXH/events.json","paper":"https://pith.science/paper/XAS53CSW"},"agent_actions":{"view_html":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH","download_json":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH.json","view_paper":"https://pith.science/paper/XAS53CSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17829&json=true","fetch_graph":"https://pith.science/api/pith-number/XAS53CSWA3IASZEQE737A6DVXH/graph.json","fetch_events":"https://pith.science/api/pith-number/XAS53CSWA3IASZEQE737A6DVXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH/action/storage_attestation","attest_author":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH/action/author_attestation","sign_citation":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH/action/citation_signature","submit_replication":"https://pith.science/pith/XAS53CSWA3IASZEQE737A6DVXH/action/replication_record"}},"created_at":"2026-07-05T11:15:17.036862+00:00","updated_at":"2026-07-05T11:15:17.036862+00:00"}