{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RCSPAJJKCCPZT7IQ5HB65BHXWK","short_pith_number":"pith:RCSPAJJK","schema_version":"1.0","canonical_sha256":"88a4f0252a109f99fd10e9c3ee84f7b289ba216afa7ddd3c813aefe9f3a466aa","source":{"kind":"arxiv","id":"2505.13940","version":2},"attestation_state":"computed","paper":{"title":"DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Jia Wu, Kun Li, Shirui Pan, Shoupeng Wang, Wenbin Hu, Zhennan Wu","submitted_at":"2025-05-20T05:18:15Z","abstract_excerpt":"Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution. However, applying LLM agents to drug discovery is still constrained by challenges such as large-scale multimodal data processing, limited task automation, and poor support for domain-specific tools. To overcome these limitations, we introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific workflows in drug discovery. DrugPilot enables multi-stage research p"},"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":"2505.13940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T05:18:15Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"3c9937b550f51dda083ad5451b0502c4735f78a0a0fe63134ebb7fd24772d3fb","abstract_canon_sha256":"b990ececa88b47dec307f630c52e1fc4e1812ddeb1e56ff9dc7141250fa9d5be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:05.848962Z","signature_b64":"XCqtWO4fs+Z7q5I9V0Hlp/+tmOY2u34bYyY6HcNLJpGj23Li9S/TH1Ewo1145Em/Lce101UU7gb9IST5E0puAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88a4f0252a109f99fd10e9c3ee84f7b289ba216afa7ddd3c813aefe9f3a466aa","last_reissued_at":"2026-07-05T11:44:05.848468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:05.848468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Jia Wu, Kun Li, Shirui Pan, Shoupeng Wang, Wenbin Hu, Zhennan Wu","submitted_at":"2025-05-20T05:18:15Z","abstract_excerpt":"Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution. However, applying LLM agents to drug discovery is still constrained by challenges such as large-scale multimodal data processing, limited task automation, and poor support for domain-specific tools. To overcome these limitations, we introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific workflows in drug discovery. DrugPilot enables multi-stage research p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13940","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/2505.13940/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":"2505.13940","created_at":"2026-07-05T11:44:05.848530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13940v2","created_at":"2026-07-05T11:44:05.848530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13940","created_at":"2026-07-05T11:44:05.848530+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCSPAJJKCCPZ","created_at":"2026-07-05T11:44:05.848530+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCSPAJJKCCPZT7IQ","created_at":"2026-07-05T11:44:05.848530+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCSPAJJK","created_at":"2026-07-05T11:44:05.848530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24013","citing_title":"UniField: RBF-Guided Electron Density Fusion for Enhanced Molecular Representations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11650","citing_title":"Large Language Model Agent for User-friendly Chemical Process Simulations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17265","citing_title":"When Molecular Similarity Works: Property Cliffs Reveal Hidden Errors","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13932","citing_title":"Rethinking Molecular OOD Generalization via Target-Aware Source Selection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10035","citing_title":"From Single-Step Edit Response to Multi-Step Molecular Optimization","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK","json":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK.json","graph_json":"https://pith.science/api/pith-number/RCSPAJJKCCPZT7IQ5HB65BHXWK/graph.json","events_json":"https://pith.science/api/pith-number/RCSPAJJKCCPZT7IQ5HB65BHXWK/events.json","paper":"https://pith.science/paper/RCSPAJJK"},"agent_actions":{"view_html":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK","download_json":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK.json","view_paper":"https://pith.science/paper/RCSPAJJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13940&json=true","fetch_graph":"https://pith.science/api/pith-number/RCSPAJJKCCPZT7IQ5HB65BHXWK/graph.json","fetch_events":"https://pith.science/api/pith-number/RCSPAJJKCCPZT7IQ5HB65BHXWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK/action/storage_attestation","attest_author":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK/action/author_attestation","sign_citation":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK/action/citation_signature","submit_replication":"https://pith.science/pith/RCSPAJJKCCPZT7IQ5HB65BHXWK/action/replication_record"}},"created_at":"2026-07-05T11:44:05.848530+00:00","updated_at":"2026-07-05T11:44:05.848530+00:00"}