{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SKMASNE3GDTPMX3YMZWAG5QUR4","short_pith_number":"pith:SKMASNE3","schema_version":"1.0","canonical_sha256":"929809349b30e6f65f78666c0376148f002afc2c7a12dbab71e339a5365a7129","source":{"kind":"arxiv","id":"2506.10912","version":4},"attestation_state":"computed","paper":{"title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chao Guo, Cong Wang, Fei Lin, Fei-Yue Wang, Gen Luo, Ji Dai, Tengchao Zhang, Xiaotong Yu, Xue Yang, Yining Jiang, Yonglin Tian, Ziyang Gong","submitted_at":"2025-06-12T17:25:53Z","abstract_excerpt":"Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced toxicity, has not yet been systematically defined or benchmarked. To fill this gap, we introduce ToxiMol, the first benchmark task for general-purpose Multimodal Large Language Models (MLLMs) focused on molecular toxicity repair. We construct a standardized dataset covering 11 primary tasks and 660 representative toxic molecules spanning diverse mechanisms "},"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":"2506.10912","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-12T17:25:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"37b1b008ce103bf2877a1530f874093a23d77d7855a5c65ba325e0e7d74292f9","abstract_canon_sha256":"714051d05fe8f5e5dca352377029ec50baaf42ae1a9865eff1dc0d58c060ce5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:43.156734Z","signature_b64":"ms1TBA70k3+xkXVh1xuaIoyk8xOIXXVVm5a4jL56ZpD9nwHkRuZxQtjFN4NV/iHoPzRuHhgXZviIyn0YqrxVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"929809349b30e6f65f78666c0376148f002afc2c7a12dbab71e339a5365a7129","last_reissued_at":"2026-06-04T00:06:43.156179Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:43.156179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chao Guo, Cong Wang, Fei Lin, Fei-Yue Wang, Gen Luo, Ji Dai, Tengchao Zhang, Xiaotong Yu, Xue Yang, Yining Jiang, Yonglin Tian, Ziyang Gong","submitted_at":"2025-06-12T17:25:53Z","abstract_excerpt":"Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced toxicity, has not yet been systematically defined or benchmarked. To fill this gap, we introduce ToxiMol, the first benchmark task for general-purpose Multimodal Large Language Models (MLLMs) focused on molecular toxicity repair. We construct a standardized dataset covering 11 primary tasks and 660 representative toxic molecules spanning diverse mechanisms "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10912","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/2506.10912/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":"2506.10912","created_at":"2026-06-04T00:06:43.156245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10912v4","created_at":"2026-06-04T00:06:43.156245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10912","created_at":"2026-06-04T00:06:43.156245+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKMASNE3GDTP","created_at":"2026-06-04T00:06:43.156245+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKMASNE3GDTPMX3Y","created_at":"2026-06-04T00:06:43.156245+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKMASNE3","created_at":"2026-06-04T00:06:43.156245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2508.12035","citing_title":"ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12181","citing_title":"MolDeTox: Evaluating Language Model's Stepwise Fragment Editing for Molecular Detoxification","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4","json":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4.json","graph_json":"https://pith.science/api/pith-number/SKMASNE3GDTPMX3YMZWAG5QUR4/graph.json","events_json":"https://pith.science/api/pith-number/SKMASNE3GDTPMX3YMZWAG5QUR4/events.json","paper":"https://pith.science/paper/SKMASNE3"},"agent_actions":{"view_html":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4","download_json":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4.json","view_paper":"https://pith.science/paper/SKMASNE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10912&json=true","fetch_graph":"https://pith.science/api/pith-number/SKMASNE3GDTPMX3YMZWAG5QUR4/graph.json","fetch_events":"https://pith.science/api/pith-number/SKMASNE3GDTPMX3YMZWAG5QUR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4/action/storage_attestation","attest_author":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4/action/author_attestation","sign_citation":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4/action/citation_signature","submit_replication":"https://pith.science/pith/SKMASNE3GDTPMX3YMZWAG5QUR4/action/replication_record"}},"created_at":"2026-06-04T00:06:43.156245+00:00","updated_at":"2026-06-04T00:06:43.156245+00:00"}