{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WF5A5HOQB57ZNSHFRM2HHPAK5P","short_pith_number":"pith:WF5A5HOQ","schema_version":"1.0","canonical_sha256":"b17a0e9dd00f7f96c8e58b3473bc0aebe8b33a991c2e6c773fedb6ddaedd5ac9","source":{"kind":"arxiv","id":"2505.16326","version":2},"attestation_state":"computed","paper":{"title":"ChemMLLM: Chemical Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongzhan Zhou, Lei Bai, Peng Xia, Qian Tan, Tianfan Fu, Wanhao Liu, Wanli Ouyang, Yuqiang Li","submitted_at":"2025-05-22T07:32:17Z","abstract_excerpt":"Multimodal large language models (MLLMs) have made impressive progress in many applications in recent years. However, chemical MLLMs that can handle cross-modal understanding and generation remain underexplored. To fill this gap, we propose ChemMLLM, a unified chemical multimodal large language model for molecule understanding and generation. Also, we design five multimodal tasks across text, molecular SMILES strings, and image, and curate the datasets. We benchmark ChemMLLM against a range of general leading MLLMs and Chemical LLMs on these tasks. Experimental results show that ChemMLLM achie"},"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":"2505.16326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T07:32:17Z","cross_cats_sorted":[],"title_canon_sha256":"e6ead6e026e483ab50045a4d9dae87a4af37981ab7d4350e89d4919eb8d3fe8b","abstract_canon_sha256":"ea366756527914a929f340460bf6125988772f59aa0203da187965a7ecaa13f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:04.061306Z","signature_b64":"/7joTSNv3JPwAoUCygo7xE32l9BBkrPI0S4JLCuVIEM5ljJYz28pgz17sbU7fVQeml5jqIoscC+MGkZJ78fTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17a0e9dd00f7f96c8e58b3473bc0aebe8b33a991c2e6c773fedb6ddaedd5ac9","last_reissued_at":"2026-07-05T11:48:04.060673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:04.060673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChemMLLM: Chemical Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongzhan Zhou, Lei Bai, Peng Xia, Qian Tan, Tianfan Fu, Wanhao Liu, Wanli Ouyang, Yuqiang Li","submitted_at":"2025-05-22T07:32:17Z","abstract_excerpt":"Multimodal large language models (MLLMs) have made impressive progress in many applications in recent years. However, chemical MLLMs that can handle cross-modal understanding and generation remain underexplored. To fill this gap, we propose ChemMLLM, a unified chemical multimodal large language model for molecule understanding and generation. Also, we design five multimodal tasks across text, molecular SMILES strings, and image, and curate the datasets. We benchmark ChemMLLM against a range of general leading MLLMs and Chemical LLMs on these tasks. Experimental results show that ChemMLLM achie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16326","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/2505.16326/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":"2505.16326","created_at":"2026-07-05T11:48:04.060758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16326v2","created_at":"2026-07-05T11:48:04.060758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16326","created_at":"2026-07-05T11:48:04.060758+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF5A5HOQB57Z","created_at":"2026-07-05T11:48:04.060758+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF5A5HOQB57ZNSHF","created_at":"2026-07-05T11:48:04.060758+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF5A5HOQ","created_at":"2026-07-05T11:48:04.060758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01982","citing_title":"MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21990","citing_title":"ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05832","citing_title":"MolRecBench-Wild: A Real-World Benchmark for Optical Chemical Structure Recognition","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P","json":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P.json","graph_json":"https://pith.science/api/pith-number/WF5A5HOQB57ZNSHFRM2HHPAK5P/graph.json","events_json":"https://pith.science/api/pith-number/WF5A5HOQB57ZNSHFRM2HHPAK5P/events.json","paper":"https://pith.science/paper/WF5A5HOQ"},"agent_actions":{"view_html":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P","download_json":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P.json","view_paper":"https://pith.science/paper/WF5A5HOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16326&json=true","fetch_graph":"https://pith.science/api/pith-number/WF5A5HOQB57ZNSHFRM2HHPAK5P/graph.json","fetch_events":"https://pith.science/api/pith-number/WF5A5HOQB57ZNSHFRM2HHPAK5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P/action/storage_attestation","attest_author":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P/action/author_attestation","sign_citation":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P/action/citation_signature","submit_replication":"https://pith.science/pith/WF5A5HOQB57ZNSHFRM2HHPAK5P/action/replication_record"}},"created_at":"2026-07-05T11:48:04.060758+00:00","updated_at":"2026-07-05T11:48:04.060758+00:00"}