{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V3FYH6XJNUHF5ZVCMJBDSRL5N4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db684c1ee6c492af250d9a4bb7d3763942bd9f51317dff611a024afe2364e3ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:08:15Z","title_canon_sha256":"6650e4c52ae7b20bc402f949d8941b16dc557fffc0af1dddfe09335e3a7f7ac5"},"schema_version":"1.0","source":{"id":"2605.21740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21740","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21740v1","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21740","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"V3FYH6XJNUHF","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"V3FYH6XJNUHF5ZVC","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"V3FYH6XJ","created_at":"2026-05-22T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:be3f408f3b7eabb1d7fd217d266be579211a6bf33b53d24257e1467e57798a75","target":"graph","created_at":"2026-05-22T01:03:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.21740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents have incredible potential for scientific discovery applications. However, the performance of LLM agents on real-world, small molecule drug design (SMDD) tasks across diverse chemistries and targets is unclear. Current evaluation methods are either ad hoc, too simple for real-world discovery, limited in scale, or restricted to single-turn question answering. In effort to standardize the evaluation of LLM agents on small molecule design, we introduce SMDD-Bench, a challenging, multi-turn, long-horizon agentic benchmark consisting of 502 guaranteed-solvable task instances spanning 5 ta","authors_text":"Amir Farimani, Hamed Mahdavi, Kathy Wei, Kevin Han, Niloofar Mireshghallah, Renfei Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:08:15Z","title":"SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21740","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db86fd1d3f343ba58a5025c4e5289d224f5fdc940749e9b58ddcbdea2eebe335","target":"record","created_at":"2026-05-22T01:03:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"db684c1ee6c492af250d9a4bb7d3763942bd9f51317dff611a024afe2364e3ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:08:15Z","title_canon_sha256":"6650e4c52ae7b20bc402f949d8941b16dc557fffc0af1dddfe09335e3a7f7ac5"},"schema_version":"1.0","source":{"id":"2605.21740","kind":"arxiv","version":1}},"canonical_sha256":"aecb83fae96d0e5ee6a2624239457d6f0733c61b2b84ca52ea41943f3370e0bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aecb83fae96d0e5ee6a2624239457d6f0733c61b2b84ca52ea41943f3370e0bc","first_computed_at":"2026-05-22T01:03:30.135661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:30.135661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icSxeIqegtJOBsgz5s6OU2dEITpyTbYy/Vv9mt9nFMx2Dfz2RUXS5ooVCk+HBZqSlPa551TRV8uQEk8GQBgnDg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:30.136361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db86fd1d3f343ba58a5025c4e5289d224f5fdc940749e9b58ddcbdea2eebe335","sha256:be3f408f3b7eabb1d7fd217d266be579211a6bf33b53d24257e1467e57798a75"],"state_sha256":"e0f6b2aeb6e1c2c075b18bad124844b8a40513098bff43fb07ea32dd0882e623"}