{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNLIJJS3RVQQN3EMUR5HCDZGXN","short_pith_number":"pith:UNLIJJS3","schema_version":"1.0","canonical_sha256":"a35684a65b8d6106ec8ca47a710f26bb714da9c5aef6f599aa76dba950f757c3","source":{"kind":"arxiv","id":"2408.11866","version":1},"attestation_state":"computed","paper":{"title":"Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Sakhinana Sagar Srinivas, Venkataramana Runkana","submitted_at":"2024-08-18T11:37:19Z","abstract_excerpt":"Molecule design is a multifaceted approach that leverages computational methods and experiments to optimize molecular properties, fast-tracking new drug discoveries, innovative material development, and more efficient chemical processes. Recently, text-based molecule design has emerged, inspired by next-generation AI tasks analogous to foundational vision-language models. Our study explores the use of knowledge-augmented prompting of large language models (LLMs) for the zero-shot text-conditional de novo molecular generation task. Our approach uses task-specific instructions and a few demonstr"},"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":"2408.11866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-18T11:37:19Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.BM"],"title_canon_sha256":"bccc55ea6ebad672c95f6891f1835a6523b45ea306f6f0492fa7affcff26faf0","abstract_canon_sha256":"0f47945284d9457e3cd8ecd1714478c34ee918db8176931bccec75f3bc5893e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:00.511116Z","signature_b64":"nOVWu5pVn6Fyhl3PmXB7r3mgteyhIQTuknMWszYMrj7PCcI2guHfBR+f1R3L9oqcFoopIXf8Lo0TY1Oya7bCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a35684a65b8d6106ec8ca47a710f26bb714da9c5aef6f599aa76dba950f757c3","last_reissued_at":"2026-07-05T08:58:00.510666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:00.510666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Sakhinana Sagar Srinivas, Venkataramana Runkana","submitted_at":"2024-08-18T11:37:19Z","abstract_excerpt":"Molecule design is a multifaceted approach that leverages computational methods and experiments to optimize molecular properties, fast-tracking new drug discoveries, innovative material development, and more efficient chemical processes. Recently, text-based molecule design has emerged, inspired by next-generation AI tasks analogous to foundational vision-language models. Our study explores the use of knowledge-augmented prompting of large language models (LLMs) for the zero-shot text-conditional de novo molecular generation task. Our approach uses task-specific instructions and a few demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11866","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/2408.11866/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":"2408.11866","created_at":"2026-07-05T08:58:00.510729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11866v1","created_at":"2026-07-05T08:58:00.510729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11866","created_at":"2026-07-05T08:58:00.510729+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNLIJJS3RVQQ","created_at":"2026-07-05T08:58:00.510729+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNLIJJS3RVQQN3EM","created_at":"2026-07-05T08:58:00.510729+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNLIJJS3","created_at":"2026-07-05T08:58:00.510729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16094","citing_title":"A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN","json":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN.json","graph_json":"https://pith.science/api/pith-number/UNLIJJS3RVQQN3EMUR5HCDZGXN/graph.json","events_json":"https://pith.science/api/pith-number/UNLIJJS3RVQQN3EMUR5HCDZGXN/events.json","paper":"https://pith.science/paper/UNLIJJS3"},"agent_actions":{"view_html":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN","download_json":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN.json","view_paper":"https://pith.science/paper/UNLIJJS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11866&json=true","fetch_graph":"https://pith.science/api/pith-number/UNLIJJS3RVQQN3EMUR5HCDZGXN/graph.json","fetch_events":"https://pith.science/api/pith-number/UNLIJJS3RVQQN3EMUR5HCDZGXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN/action/storage_attestation","attest_author":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN/action/author_attestation","sign_citation":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN/action/citation_signature","submit_replication":"https://pith.science/pith/UNLIJJS3RVQQN3EMUR5HCDZGXN/action/replication_record"}},"created_at":"2026-07-05T08:58:00.510729+00:00","updated_at":"2026-07-05T08:58:00.510729+00:00"}