{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F2Y6GGZ77WQMXKVOMXBFCRPVL4","short_pith_number":"pith:F2Y6GGZ7","schema_version":"1.0","canonical_sha256":"2eb1e31b3ffda0cbaaae65c25145f55f0fe93866c2d395b06083bc23b00b1eea","source":{"kind":"arxiv","id":"2405.16205","version":1},"attestation_state":"computed","paper":{"title":"GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chih-Hsuan Wei, Chi-Ping Day, Christina Ross, Po-Ting Lai, Qiao Jin, Qingqing Zhu, Shubo Tian, Zhiyong Lu, Zhizheng Wang","submitted_at":"2024-05-25T12:35:15Z","abstract_excerpt":"Gene set knowledge discovery is essential for advancing human functional genomics. Recent studies have shown promising performance by harnessing the power of Large Language Models (LLMs) on this task. Nonetheless, their results are subject to several limitations common in LLMs such as hallucinations. In response, we present GeneAgent, a first-of-its-kind language agent featuring self-verification capability. It autonomously interacts with various biological databases and leverages relevant domain knowledge to improve accuracy and reduce hallucination occurrences. Benchmarking on 1,106 gene set"},"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":"2405.16205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-25T12:35:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a85e51b7ae323b7cb01bbbf73931ea48bee6dec1315ea1c942dcc257397895ac","abstract_canon_sha256":"46968e5bfc48f939fb3c6e35575ed1d654656311beb8715314fc359dea497e38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:27.219059Z","signature_b64":"7HVDf2ymOTjNjBHUofwK1/TTQ/rXCQWxKD5vU9M5jZYkM4SCN7LKOt83KFdCnbVilVLlQy+COlk0UZDwgX/1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eb1e31b3ffda0cbaaae65c25145f55f0fe93866c2d395b06083bc23b00b1eea","last_reissued_at":"2026-07-05T08:23:27.218615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:27.218615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chih-Hsuan Wei, Chi-Ping Day, Christina Ross, Po-Ting Lai, Qiao Jin, Qingqing Zhu, Shubo Tian, Zhiyong Lu, Zhizheng Wang","submitted_at":"2024-05-25T12:35:15Z","abstract_excerpt":"Gene set knowledge discovery is essential for advancing human functional genomics. Recent studies have shown promising performance by harnessing the power of Large Language Models (LLMs) on this task. Nonetheless, their results are subject to several limitations common in LLMs such as hallucinations. In response, we present GeneAgent, a first-of-its-kind language agent featuring self-verification capability. It autonomously interacts with various biological databases and leverages relevant domain knowledge to improve accuracy and reduce hallucination occurrences. Benchmarking on 1,106 gene set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16205","kind":"arxiv","version":1},"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/2405.16205/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":"2405.16205","created_at":"2026-07-05T08:23:27.218670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16205v1","created_at":"2026-07-05T08:23:27.218670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16205","created_at":"2026-07-05T08:23:27.218670+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2Y6GGZ77WQM","created_at":"2026-07-05T08:23:27.218670+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2Y6GGZ77WQMXKVO","created_at":"2026-07-05T08:23:27.218670+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2Y6GGZ7","created_at":"2026-07-05T08:23:27.218670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":274,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":142,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4","json":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4.json","graph_json":"https://pith.science/api/pith-number/F2Y6GGZ77WQMXKVOMXBFCRPVL4/graph.json","events_json":"https://pith.science/api/pith-number/F2Y6GGZ77WQMXKVOMXBFCRPVL4/events.json","paper":"https://pith.science/paper/F2Y6GGZ7"},"agent_actions":{"view_html":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4","download_json":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4.json","view_paper":"https://pith.science/paper/F2Y6GGZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16205&json=true","fetch_graph":"https://pith.science/api/pith-number/F2Y6GGZ77WQMXKVOMXBFCRPVL4/graph.json","fetch_events":"https://pith.science/api/pith-number/F2Y6GGZ77WQMXKVOMXBFCRPVL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4/action/storage_attestation","attest_author":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4/action/author_attestation","sign_citation":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4/action/citation_signature","submit_replication":"https://pith.science/pith/F2Y6GGZ77WQMXKVOMXBFCRPVL4/action/replication_record"}},"created_at":"2026-07-05T08:23:27.218670+00:00","updated_at":"2026-07-05T08:23:27.218670+00:00"}