{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QV4K6KIFKEFUKCKFFEDZYEOG3U","short_pith_number":"pith:QV4K6KIF","schema_version":"1.0","canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","source":{"kind":"arxiv","id":"2306.08018","version":5},"attestation_state":"computed","paper":{"title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Huajun Chen, Kangwei Liu, Ningyu Zhang, Rui Huang, Xiaohui Fan, Xiaozhuan Liang, Yin Fang, Zhuo Chen","submitted_at":"2023-06-13T14:35:34Z","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"},"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":"2306.08018","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a","abstract_canon_sha256":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:29.594648Z","signature_b64":"ER1zt00/rbqhuYH5BmIZE+JMd4mc3Go7SJBJUdUevLvohgZ7fU7Kbg7nf9h8A1RN1gfStJWNcxbtk9Q91/ywDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","last_reissued_at":"2026-07-05T07:51:29.594131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:29.594131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Huajun Chen, Kangwei Liu, Ningyu Zhang, Rui Huang, Xiaohui Fan, Xiaozhuan Liang, Yin Fang, Zhuo Chen","submitted_at":"2023-06-13T14:35:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08018","kind":"arxiv","version":5},"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/2306.08018/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":"2306.08018","created_at":"2026-07-05T07:51:29.594192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08018v5","created_at":"2026-07-05T07:51:29.594192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08018","created_at":"2026-07-05T07:51:29.594192+00:00"},{"alias_kind":"pith_short_12","alias_value":"QV4K6KIFKEFU","created_at":"2026-07-05T07:51:29.594192+00:00"},{"alias_kind":"pith_short_16","alias_value":"QV4K6KIFKEFUKCKF","created_at":"2026-07-05T07:51:29.594192+00:00"},{"alias_kind":"pith_short_8","alias_value":"QV4K6KIF","created_at":"2026-07-05T07:51:29.594192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07954","citing_title":"Minibatch Selection for Language Models via Partition Matroid Constrained Gradient Matching","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05693","citing_title":"MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04579","citing_title":"SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03057","citing_title":"Rethinking Molecular Text Representations for LLMs: An Empirical Study","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22287","citing_title":"SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20740","citing_title":"Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10978","citing_title":"VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10978","citing_title":"VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10230","citing_title":"FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04403","citing_title":"MolDA: Molecular Understanding and Generation via Large Language Diffusion Model","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U","json":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U.json","graph_json":"https://pith.science/api/pith-number/QV4K6KIFKEFUKCKFFEDZYEOG3U/graph.json","events_json":"https://pith.science/api/pith-number/QV4K6KIFKEFUKCKFFEDZYEOG3U/events.json","paper":"https://pith.science/paper/QV4K6KIF"},"agent_actions":{"view_html":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U","download_json":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U.json","view_paper":"https://pith.science/paper/QV4K6KIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08018&json=true","fetch_graph":"https://pith.science/api/pith-number/QV4K6KIFKEFUKCKFFEDZYEOG3U/graph.json","fetch_events":"https://pith.science/api/pith-number/QV4K6KIFKEFUKCKFFEDZYEOG3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/action/storage_attestation","attest_author":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/action/author_attestation","sign_citation":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/action/citation_signature","submit_replication":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/action/replication_record"}},"created_at":"2026-07-05T07:51:29.594192+00:00","updated_at":"2026-07-05T07:51:29.594192+00:00"}