{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EP3BJRTCQXCWWRNTE2HTWV544U","short_pith_number":"pith:EP3BJRTC","schema_version":"1.0","canonical_sha256":"23f614c66285c56b45b3268f3b57bce53250e044c849b103a85d56658134ac42","source":{"kind":"arxiv","id":"2410.21591","version":2},"attestation_state":"computed","paper":{"title":"Can Large Language Models Replace Data Scientists in Biomedical Research?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.GN","q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Benjamin Danek, Jimeng Sun, Zheng Chen, Zifeng Wang, Ziwei Yang","submitted_at":"2024-10-28T22:48:06Z","abstract_excerpt":"Data science plays a critical role in biomedical research, but it requires professionals with expertise in coding and medical data analysis. Large language models (LLMs) have shown great potential in supporting medical tasks and performing well in general coding tests. However, existing evaluations fail to assess their capability in biomedical data science, particularly in handling diverse data types such as genomics and clinical datasets. To address this gap, we developed a benchmark of data science coding tasks derived from the analyses of 39 published studies. This benchmark comprises 293 c"},"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":"2410.21591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-28T22:48:06Z","cross_cats_sorted":["cs.CL","q-bio.GN","q-bio.QM"],"title_canon_sha256":"4e052054a4a8ea761745a1ee6bc2694d1d1f4c8a9f612b51af59b3af76d92be6","abstract_canon_sha256":"1415c21db3dd55c5f4fa1e57ea47d2a5e45916ba1bb18521e5e43740ade11618"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:21.209336Z","signature_b64":"2prcWzgVx31msgynlSSV8NyxFCIsgh6tN3m11qu+zhwV+zLXruQB7E7BGrH1dIc7kSpIn29cIYkTNZyhDV7lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23f614c66285c56b45b3268f3b57bce53250e044c849b103a85d56658134ac42","last_reissued_at":"2026-07-05T10:46:21.208820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:21.208820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Replace Data Scientists in Biomedical Research?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.GN","q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Benjamin Danek, Jimeng Sun, Zheng Chen, Zifeng Wang, Ziwei Yang","submitted_at":"2024-10-28T22:48:06Z","abstract_excerpt":"Data science plays a critical role in biomedical research, but it requires professionals with expertise in coding and medical data analysis. Large language models (LLMs) have shown great potential in supporting medical tasks and performing well in general coding tests. However, existing evaluations fail to assess their capability in biomedical data science, particularly in handling diverse data types such as genomics and clinical datasets. To address this gap, we developed a benchmark of data science coding tasks derived from the analyses of 39 published studies. This benchmark comprises 293 c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21591","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/2410.21591/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":"2410.21591","created_at":"2026-07-05T10:46:21.208881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21591v2","created_at":"2026-07-05T10:46:21.208881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21591","created_at":"2026-07-05T10:46:21.208881+00:00"},{"alias_kind":"pith_short_12","alias_value":"EP3BJRTCQXCW","created_at":"2026-07-05T10:46:21.208881+00:00"},{"alias_kind":"pith_short_16","alias_value":"EP3BJRTCQXCWWRNT","created_at":"2026-07-05T10:46:21.208881+00:00"},{"alias_kind":"pith_short_8","alias_value":"EP3BJRTC","created_at":"2026-07-05T10:46:21.208881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16679","citing_title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U","json":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U.json","graph_json":"https://pith.science/api/pith-number/EP3BJRTCQXCWWRNTE2HTWV544U/graph.json","events_json":"https://pith.science/api/pith-number/EP3BJRTCQXCWWRNTE2HTWV544U/events.json","paper":"https://pith.science/paper/EP3BJRTC"},"agent_actions":{"view_html":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U","download_json":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U.json","view_paper":"https://pith.science/paper/EP3BJRTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21591&json=true","fetch_graph":"https://pith.science/api/pith-number/EP3BJRTCQXCWWRNTE2HTWV544U/graph.json","fetch_events":"https://pith.science/api/pith-number/EP3BJRTCQXCWWRNTE2HTWV544U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U/action/storage_attestation","attest_author":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U/action/author_attestation","sign_citation":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U/action/citation_signature","submit_replication":"https://pith.science/pith/EP3BJRTCQXCWWRNTE2HTWV544U/action/replication_record"}},"created_at":"2026-07-05T10:46:21.208881+00:00","updated_at":"2026-07-05T10:46:21.208881+00:00"}