{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6VDBCJ6ILJS4IYN6QRLXMIXWC2","short_pith_number":"pith:6VDBCJ6I","schema_version":"1.0","canonical_sha256":"f5461127c85a65c461be84577622f616aee642607d7b9fa9036d9c0edf409c4b","source":{"kind":"arxiv","id":"2505.07865","version":1},"attestation_state":"computed","paper":{"title":"CellVerse: Do Large Language Models Really Understand Cell Biology?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","q-bio.CB"],"primary_cat":"q-bio.QM","authors_text":"Donghao Zhou, Fan Zhang, Haixin Wang, Hao Wu, Kun Wang, Pheng-Ann Heng, Tianyu Liu, Xian Wu, Yefeng Zheng, Zhihong Zhu","submitted_at":"2025-05-09T06:47:23Z","abstract_excerpt":"Recent studies have demonstrated the feasibility of modeling single-cell data as natural languages and the potential of leveraging powerful large language models (LLMs) for understanding cell biology. However, a comprehensive evaluation of LLMs' performance on language-driven single-cell analysis tasks still remains unexplored. Motivated by this challenge, we introduce CellVerse, a unified language-centric question-answering benchmark that integrates four types of single-cell multi-omics data and encompasses three hierarchical levels of single-cell analysis tasks: cell type annotation (cell-le"},"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":"2505.07865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-05-09T06:47:23Z","cross_cats_sorted":["cs.AI","cs.CL","q-bio.CB"],"title_canon_sha256":"81b97416950070bc0a34647ec9578db045802c367ca672b095693464cbae68f7","abstract_canon_sha256":"a7f0a029e8d8fa670a1dc649620ba29765839ecce34c111648c0d9708420a28d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:58.418898Z","signature_b64":"erH7tGIlo64PE4w2EXWUOLABliAVjbHlboBcQmRmpMklKfsSAuT90E4FU6pi9LzstkFeSRbtGYsgJtGxborbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5461127c85a65c461be84577622f616aee642607d7b9fa9036d9c0edf409c4b","last_reissued_at":"2026-07-05T11:01:58.418427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:58.418427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CellVerse: Do Large Language Models Really Understand Cell Biology?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","q-bio.CB"],"primary_cat":"q-bio.QM","authors_text":"Donghao Zhou, Fan Zhang, Haixin Wang, Hao Wu, Kun Wang, Pheng-Ann Heng, Tianyu Liu, Xian Wu, Yefeng Zheng, Zhihong Zhu","submitted_at":"2025-05-09T06:47:23Z","abstract_excerpt":"Recent studies have demonstrated the feasibility of modeling single-cell data as natural languages and the potential of leveraging powerful large language models (LLMs) for understanding cell biology. However, a comprehensive evaluation of LLMs' performance on language-driven single-cell analysis tasks still remains unexplored. Motivated by this challenge, we introduce CellVerse, a unified language-centric question-answering benchmark that integrates four types of single-cell multi-omics data and encompasses three hierarchical levels of single-cell analysis tasks: cell type annotation (cell-le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07865","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/2505.07865/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":"2505.07865","created_at":"2026-07-05T11:01:58.418488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07865v1","created_at":"2026-07-05T11:01:58.418488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07865","created_at":"2026-07-05T11:01:58.418488+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VDBCJ6ILJS4","created_at":"2026-07-05T11:01:58.418488+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VDBCJ6ILJS4IYN6","created_at":"2026-07-05T11:01:58.418488+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VDBCJ6I","created_at":"2026-07-05T11:01:58.418488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2","json":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2.json","graph_json":"https://pith.science/api/pith-number/6VDBCJ6ILJS4IYN6QRLXMIXWC2/graph.json","events_json":"https://pith.science/api/pith-number/6VDBCJ6ILJS4IYN6QRLXMIXWC2/events.json","paper":"https://pith.science/paper/6VDBCJ6I"},"agent_actions":{"view_html":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2","download_json":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2.json","view_paper":"https://pith.science/paper/6VDBCJ6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07865&json=true","fetch_graph":"https://pith.science/api/pith-number/6VDBCJ6ILJS4IYN6QRLXMIXWC2/graph.json","fetch_events":"https://pith.science/api/pith-number/6VDBCJ6ILJS4IYN6QRLXMIXWC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2/action/storage_attestation","attest_author":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2/action/author_attestation","sign_citation":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2/action/citation_signature","submit_replication":"https://pith.science/pith/6VDBCJ6ILJS4IYN6QRLXMIXWC2/action/replication_record"}},"created_at":"2026-07-05T11:01:58.418488+00:00","updated_at":"2026-07-05T11:01:58.418488+00:00"}