{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VLMG63SJV5JAOKBMUR227O63MV","short_pith_number":"pith:VLMG63SJ","schema_version":"1.0","canonical_sha256":"aad86f6e49af5207282ca475afbbdb6548d5340a19d0bee17d93a4fc8d7b6470","source":{"kind":"arxiv","id":"2502.02810","version":2},"attestation_state":"computed","paper":{"title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Chanhui Lee, Hanbum Ko, Kyunghoon Bae, Rodrigo Hormazabal, Sehui Han, Sungbin Lim, Sungwoong Kim, YongJun Jeong, Yuheon Song","submitted_at":"2025-02-05T01:14:12Z","abstract_excerpt":"Recent advances in large language models (LLMs) have led to models that tackle diverse molecular tasks, such as chemical reaction prediction and molecular property prediction. Large-scale molecular instruction-tuning datasets have enabled sequence-only (e.g., SMILES or SELFIES) generalist molecular LLMs, and researchers are now exploring multimodal approaches that incorporate molecular structural information for further gains. However, a genuinely multimodal, generalist LLM that covers a broad spectrum of molecular tasks has yet to be fully investigated. We observe that naive next token predic"},"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":"2502.02810","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T01:14:12Z","cross_cats_sorted":["cs.AI","physics.chem-ph","q-bio.BM"],"title_canon_sha256":"fe5948594663e6a6afaba99965d6ee3da2e29c30f16bbaf24468ae7a73b6fc35","abstract_canon_sha256":"e0aa0096cb9e42ab3e8a13c2739ff9958ac9e01af2747ffc31e6790a2ae81c47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:07.629958Z","signature_b64":"AiP7btXguQXnxJxo5U6ZiUXUNd170Vy/eZqLXJVOHoj55tAa6HYcOZpICTZaHGWmT3S06PXYqD740LIEOVJUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad86f6e49af5207282ca475afbbdb6548d5340a19d0bee17d93a4fc8d7b6470","last_reissued_at":"2026-07-05T11:09:07.629460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:07.629460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Chanhui Lee, Hanbum Ko, Kyunghoon Bae, Rodrigo Hormazabal, Sehui Han, Sungbin Lim, Sungwoong Kim, YongJun Jeong, Yuheon Song","submitted_at":"2025-02-05T01:14:12Z","abstract_excerpt":"Recent advances in large language models (LLMs) have led to models that tackle diverse molecular tasks, such as chemical reaction prediction and molecular property prediction. Large-scale molecular instruction-tuning datasets have enabled sequence-only (e.g., SMILES or SELFIES) generalist molecular LLMs, and researchers are now exploring multimodal approaches that incorporate molecular structural information for further gains. However, a genuinely multimodal, generalist LLM that covers a broad spectrum of molecular tasks has yet to be fully investigated. We observe that naive next token predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02810","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/2502.02810/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":"2502.02810","created_at":"2026-07-05T11:09:07.629519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02810v2","created_at":"2026-07-05T11:09:07.629519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02810","created_at":"2026-07-05T11:09:07.629519+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLMG63SJV5JA","created_at":"2026-07-05T11:09:07.629519+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLMG63SJV5JAOKBM","created_at":"2026-07-05T11:09:07.629519+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLMG63SJ","created_at":"2026-07-05T11:09:07.629519+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08404","citing_title":"DrugGen 2: A disease-aware language model for enhancing drug discovery","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04403","citing_title":"MolDA: Molecular Understanding and Generation via Large Language Diffusion Model","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV","json":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV.json","graph_json":"https://pith.science/api/pith-number/VLMG63SJV5JAOKBMUR227O63MV/graph.json","events_json":"https://pith.science/api/pith-number/VLMG63SJV5JAOKBMUR227O63MV/events.json","paper":"https://pith.science/paper/VLMG63SJ"},"agent_actions":{"view_html":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV","download_json":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV.json","view_paper":"https://pith.science/paper/VLMG63SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02810&json=true","fetch_graph":"https://pith.science/api/pith-number/VLMG63SJV5JAOKBMUR227O63MV/graph.json","fetch_events":"https://pith.science/api/pith-number/VLMG63SJV5JAOKBMUR227O63MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV/action/storage_attestation","attest_author":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV/action/author_attestation","sign_citation":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV/action/citation_signature","submit_replication":"https://pith.science/pith/VLMG63SJV5JAOKBMUR227O63MV/action/replication_record"}},"created_at":"2026-07-05T11:09:07.629519+00:00","updated_at":"2026-07-05T11:09:07.629519+00:00"}