{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QV4K6KIFKEFUKCKFFEDZYEOG3U","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":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a"},"schema_version":"1.0","source":{"id":"2306.08018","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08018","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08018v5","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08018","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"QV4K6KIFKEFU","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"QV4K6KIFKEFUKCKF","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"QV4K6KIF","created_at":"2026-07-05T07:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:1cb15b2f9cb595d98d4d7c3061f192b68b01690205edcfa0250799ed24a011dc","target":"graph","created_at":"2026-07-05T07:51:29Z","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/2306.08018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, we introduce Mol-Instructions, a comprehensive instruction dataset designed for the biomolecular domain. Mol-Instructions encompasses three key components: molecule-oriented instructions, protein-oriented instructions, and biomolecular text instructions. Each component aims to improve the understandi","authors_text":"Huajun Chen, Kangwei Liu, Ningyu Zhang, Rui Huang, Xiaohui Fan, Xiaozhuan Liang, Yin Fang, Zhuo Chen","cross_cats":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08018","kind":"arxiv","version":5},"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:dbea950128b1852812ee4268f5b32b23120c1daf7bb06a4338ccf680cff9e80c","target":"record","created_at":"2026-07-05T07:51:29Z","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":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a"},"schema_version":"1.0","source":{"id":"2306.08018","kind":"arxiv","version":5}},"canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","first_computed_at":"2026-07-05T07:51:29.594131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:29.594131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ER1zt00/rbqhuYH5BmIZE+JMd4mc3Go7SJBJUdUevLvohgZ7fU7Kbg7nf9h8A1RN1gfStJWNcxbtk9Q91/ywDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:29.594648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08018","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbea950128b1852812ee4268f5b32b23120c1daf7bb06a4338ccf680cff9e80c","sha256:1cb15b2f9cb595d98d4d7c3061f192b68b01690205edcfa0250799ed24a011dc"],"state_sha256":"90d9c743f0491bab8cc0681c8a484e92f613e4e77b89e685eca911e798fe2558"}