{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4QOLF2QMGPC4722DZCDXN3Q77T","short_pith_number":"pith:4QOLF2QM","schema_version":"1.0","canonical_sha256":"e41cb2ea0c33c5cfeb43c88776ee1ffcda531eaaf04bfeb244cf3e6ceb9c6c8a","source":{"kind":"arxiv","id":"2407.08940","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biqing Qi, Bowen Zhou, Ermo Hua, Haoxiang Li, Hu Jinfang, Kai Tian, Kaiyan Zhang, Sihang Zeng, Zhang-Ren Chen","submitted_at":"2024-07-12T02:55:13Z","abstract_excerpt":"The rapid growth of biomedical knowledge has outpaced our ability to efficiently extract insights and generate novel hypotheses. Large language models (LLMs) have emerged as a promising tool to revolutionize knowledge interaction and potentially accelerate biomedical discovery. In this paper, we present a comprehensive evaluation of LLMs as biomedical hypothesis generators. We construct a dataset of background-hypothesis pairs from biomedical literature, carefully partitioned into training, seen, and unseen test sets based on publication date to mitigate data contamination. Using this dataset,"},"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":"2407.08940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T02:55:13Z","cross_cats_sorted":[],"title_canon_sha256":"a1e547ee712f2ee2ab5d996796c06f389353089a3334668348d4ea9df7a51753","abstract_canon_sha256":"5ddf7ee27930662e9876ce6b9652f108e01e0d1db36ac21054bfa06ec6364408"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:57.661466Z","signature_b64":"eGYqoK9H3NrSBl1tvXATfd7R6q87wQt8R6gLQB6bpNv8Mg87MXBDPQU54CvP8IfHem6a+evrb5j6l1SMZa5bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e41cb2ea0c33c5cfeb43c88776ee1ffcda531eaaf04bfeb244cf3e6ceb9c6c8a","last_reissued_at":"2026-07-05T08:43:57.660979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:57.660979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biqing Qi, Bowen Zhou, Ermo Hua, Haoxiang Li, Hu Jinfang, Kai Tian, Kaiyan Zhang, Sihang Zeng, Zhang-Ren Chen","submitted_at":"2024-07-12T02:55:13Z","abstract_excerpt":"The rapid growth of biomedical knowledge has outpaced our ability to efficiently extract insights and generate novel hypotheses. Large language models (LLMs) have emerged as a promising tool to revolutionize knowledge interaction and potentially accelerate biomedical discovery. In this paper, we present a comprehensive evaluation of LLMs as biomedical hypothesis generators. We construct a dataset of background-hypothesis pairs from biomedical literature, carefully partitioned into training, seen, and unseen test sets based on publication date to mitigate data contamination. Using this dataset,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08940","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/2407.08940/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":"2407.08940","created_at":"2026-07-05T08:43:57.661031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08940v2","created_at":"2026-07-05T08:43:57.661031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08940","created_at":"2026-07-05T08:43:57.661031+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QOLF2QMGPC4","created_at":"2026-07-05T08:43:57.661031+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QOLF2QMGPC4722D","created_at":"2026-07-05T08:43:57.661031+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QOLF2QM","created_at":"2026-07-05T08:43:57.661031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08532","citing_title":"DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":272,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15588","citing_title":"\"Excuse me, may I say something...\" CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T","json":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T.json","graph_json":"https://pith.science/api/pith-number/4QOLF2QMGPC4722DZCDXN3Q77T/graph.json","events_json":"https://pith.science/api/pith-number/4QOLF2QMGPC4722DZCDXN3Q77T/events.json","paper":"https://pith.science/paper/4QOLF2QM"},"agent_actions":{"view_html":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T","download_json":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T.json","view_paper":"https://pith.science/paper/4QOLF2QM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08940&json=true","fetch_graph":"https://pith.science/api/pith-number/4QOLF2QMGPC4722DZCDXN3Q77T/graph.json","fetch_events":"https://pith.science/api/pith-number/4QOLF2QMGPC4722DZCDXN3Q77T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T/action/storage_attestation","attest_author":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T/action/author_attestation","sign_citation":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T/action/citation_signature","submit_replication":"https://pith.science/pith/4QOLF2QMGPC4722DZCDXN3Q77T/action/replication_record"}},"created_at":"2026-07-05T08:43:57.661031+00:00","updated_at":"2026-07-05T08:43:57.661031+00:00"}