{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4MI4MCB6X6XRAD57QAXZMQRDXV","short_pith_number":"pith:4MI4MCB6","schema_version":"1.0","canonical_sha256":"e311c6083ebfaf100fbf802f964223bd6a54292e23d2826cd6b6eabfa50ec5ee","source":{"kind":"arxiv","id":"2406.15341","version":3},"attestation_state":"computed","paper":{"title":"GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Haohan Wang, Haoyang Liu, Shuyu Chen, Ye Zhang","submitted_at":"2024-06-21T17:55:24Z","abstract_excerpt":"Recent advancements in machine learning have significantly improved the identification of disease-associated genes from gene expression datasets. However, these processes often require extensive expertise and manual effort, limiting their scalability. Large Language Model (LLM)-based agents have shown promise in automating these tasks due to their increasing problem-solving abilities. To support the evaluation and development of such methods, we introduce GenoTEX, a benchmark dataset for the automated analysis of gene expression data. GenoTEX provides analysis code and results for solving a wi"},"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":"2406.15341","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T17:55:24Z","cross_cats_sorted":["cs.AI","q-bio.GN"],"title_canon_sha256":"8214ffab70434934384418b72ff9b96bd8f8c366e80f03d8da99239f5a864dfd","abstract_canon_sha256":"efe4326326843b64c4b5660511c2290b44992fa76cf8faf71355e497bb707838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:53.318745Z","signature_b64":"dYEicihyzeiePTXJkyGEerbeJO7lhGD82kKzrERt0z9ywiB0j8G1sLN/VAXrDxj114snLvg2U41QbziLdpoRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e311c6083ebfaf100fbf802f964223bd6a54292e23d2826cd6b6eabfa50ec5ee","last_reissued_at":"2026-07-05T10:45:53.318207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:53.318207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Haohan Wang, Haoyang Liu, Shuyu Chen, Ye Zhang","submitted_at":"2024-06-21T17:55:24Z","abstract_excerpt":"Recent advancements in machine learning have significantly improved the identification of disease-associated genes from gene expression datasets. However, these processes often require extensive expertise and manual effort, limiting their scalability. Large Language Model (LLM)-based agents have shown promise in automating these tasks due to their increasing problem-solving abilities. To support the evaluation and development of such methods, we introduce GenoTEX, a benchmark dataset for the automated analysis of gene expression data. GenoTEX provides analysis code and results for solving a wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15341","kind":"arxiv","version":3},"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/2406.15341/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":"2406.15341","created_at":"2026-07-05T10:45:53.318268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15341v3","created_at":"2026-07-05T10:45:53.318268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15341","created_at":"2026-07-05T10:45:53.318268+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MI4MCB6X6XR","created_at":"2026-07-05T10:45:53.318268+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MI4MCB6X6XRAD57","created_at":"2026-07-05T10:45:53.318268+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MI4MCB6","created_at":"2026-07-05T10:45:53.318268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV","json":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV.json","graph_json":"https://pith.science/api/pith-number/4MI4MCB6X6XRAD57QAXZMQRDXV/graph.json","events_json":"https://pith.science/api/pith-number/4MI4MCB6X6XRAD57QAXZMQRDXV/events.json","paper":"https://pith.science/paper/4MI4MCB6"},"agent_actions":{"view_html":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV","download_json":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV.json","view_paper":"https://pith.science/paper/4MI4MCB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15341&json=true","fetch_graph":"https://pith.science/api/pith-number/4MI4MCB6X6XRAD57QAXZMQRDXV/graph.json","fetch_events":"https://pith.science/api/pith-number/4MI4MCB6X6XRAD57QAXZMQRDXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV/action/storage_attestation","attest_author":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV/action/author_attestation","sign_citation":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV/action/citation_signature","submit_replication":"https://pith.science/pith/4MI4MCB6X6XRAD57QAXZMQRDXV/action/replication_record"}},"created_at":"2026-07-05T10:45:53.318268+00:00","updated_at":"2026-07-05T10:45:53.318268+00:00"}