{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BN4NCN7FLIDSD674KAEGZUIQOY","short_pith_number":"pith:BN4NCN7F","schema_version":"1.0","canonical_sha256":"0b78d137e55a0721fbfc50086cd110763d7ff404589cb278918d0c3691e133fc","source":{"kind":"arxiv","id":"2508.14748","version":1},"attestation_state":"computed","paper":{"title":"Cross-Modality Controlled Molecule Generation with Diffusion Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Khanh Vinh Nguyen, Pengyu Hong, Yifei Wang, Yunzhe Zhang","submitted_at":"2025-08-20T14:48:44Z","abstract_excerpt":"Current SMILES-based diffusion models for molecule generation typically support only unimodal constraint. They inject conditioning signals at the start of the training process and require retraining a new model from scratch whenever the constraint changes. However, real-world applications often involve multiple constraints across different modalities, and additional constraints may emerge over the course of a study. This raises a challenge: how to extend a pre-trained diffusion model not only to support cross-modality constraints but also to incorporate new ones without retraining. To tackle t"},"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":"2508.14748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T14:48:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f50c489ec222f26ce06ccdf36159c476fda12f7ada6e8443ce0584c77856480","abstract_canon_sha256":"f4bd10cd0f989b6fc417b22fedc6c98e114906012876a29913bca44e975f5a37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:37.968420Z","signature_b64":"FADOl1ujdHITiM1pxGSyXejw2P27MtWDMb4U2XuYwxVvL8GOKhLxe+Th3irnnUd9Dzwj6SZIvElRfk2V0Un3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b78d137e55a0721fbfc50086cd110763d7ff404589cb278918d0c3691e133fc","last_reissued_at":"2026-07-05T11:56:37.967994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:37.967994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modality Controlled Molecule Generation with Diffusion Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Khanh Vinh Nguyen, Pengyu Hong, Yifei Wang, Yunzhe Zhang","submitted_at":"2025-08-20T14:48:44Z","abstract_excerpt":"Current SMILES-based diffusion models for molecule generation typically support only unimodal constraint. They inject conditioning signals at the start of the training process and require retraining a new model from scratch whenever the constraint changes. However, real-world applications often involve multiple constraints across different modalities, and additional constraints may emerge over the course of a study. This raises a challenge: how to extend a pre-trained diffusion model not only to support cross-modality constraints but also to incorporate new ones without retraining. To tackle t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14748","kind":"arxiv","version":1},"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/2508.14748/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":"2508.14748","created_at":"2026-07-05T11:56:37.968051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14748v1","created_at":"2026-07-05T11:56:37.968051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14748","created_at":"2026-07-05T11:56:37.968051+00:00"},{"alias_kind":"pith_short_12","alias_value":"BN4NCN7FLIDS","created_at":"2026-07-05T11:56:37.968051+00:00"},{"alias_kind":"pith_short_16","alias_value":"BN4NCN7FLIDSD674","created_at":"2026-07-05T11:56:37.968051+00:00"},{"alias_kind":"pith_short_8","alias_value":"BN4NCN7F","created_at":"2026-07-05T11:56:37.968051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY","json":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY.json","graph_json":"https://pith.science/api/pith-number/BN4NCN7FLIDSD674KAEGZUIQOY/graph.json","events_json":"https://pith.science/api/pith-number/BN4NCN7FLIDSD674KAEGZUIQOY/events.json","paper":"https://pith.science/paper/BN4NCN7F"},"agent_actions":{"view_html":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY","download_json":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY.json","view_paper":"https://pith.science/paper/BN4NCN7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14748&json=true","fetch_graph":"https://pith.science/api/pith-number/BN4NCN7FLIDSD674KAEGZUIQOY/graph.json","fetch_events":"https://pith.science/api/pith-number/BN4NCN7FLIDSD674KAEGZUIQOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY/action/storage_attestation","attest_author":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY/action/author_attestation","sign_citation":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY/action/citation_signature","submit_replication":"https://pith.science/pith/BN4NCN7FLIDSD674KAEGZUIQOY/action/replication_record"}},"created_at":"2026-07-05T11:56:37.968051+00:00","updated_at":"2026-07-05T11:56:37.968051+00:00"}