{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MIY7RWZ24DGUFBYOL2MCO4KE73","short_pith_number":"pith:MIY7RWZ2","schema_version":"1.0","canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","source":{"kind":"arxiv","id":"2404.18443","version":2},"attestation_state":"computed","paper":{"title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Chao Zhang, Joyce C. Ho, May D. Wang, Ran Xu, Wenqi Shi, Yanqiao Zhu, Yuchen Zhuang, Yue Yu","submitted_at":"2024-04-29T05:40:08Z","abstract_excerpt":"Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We present BMRetriever, a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedical corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs. Experiments on 5 biomedical tasks across 11 datasets verify BMRetriever's efficacy on various biomedical applications. BM"},"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":"2404.18443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T05:40:08Z","cross_cats_sorted":["cs.AI","cs.IR","q-bio.QM"],"title_canon_sha256":"91ceb568ede924767fcba9bc52c215a9b01c0041b0f8a6538e5e2a5aad95473f","abstract_canon_sha256":"edfbd581f77ef2747a4d9ddbf1f4bb7b4bec2cfb6464cffece9cc8d709933b1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:31.861496Z","signature_b64":"LRjGXAqGEkXuFAIZBuuFbs9UPLeoTExOtdO6wumgHemj3O+ea9O5bUbdxFkjJIoKqdUM58qKxJl/S3mCUQxpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","last_reissued_at":"2026-07-05T09:15:31.860976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:31.860976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Chao Zhang, Joyce C. Ho, May D. Wang, Ran Xu, Wenqi Shi, Yanqiao Zhu, Yuchen Zhuang, Yue Yu","submitted_at":"2024-04-29T05:40:08Z","abstract_excerpt":"Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We present BMRetriever, a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedical corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs. Experiments on 5 biomedical tasks across 11 datasets verify BMRetriever's efficacy on various biomedical applications. BM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18443","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/2404.18443/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":"2404.18443","created_at":"2026-07-05T09:15:31.861031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18443v2","created_at":"2026-07-05T09:15:31.861031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18443","created_at":"2026-07-05T09:15:31.861031+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIY7RWZ24DGU","created_at":"2026-07-05T09:15:31.861031+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIY7RWZ24DGUFBYO","created_at":"2026-07-05T09:15:31.861031+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIY7RWZ2","created_at":"2026-07-05T09:15:31.861031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18146","citing_title":"Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73","json":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73.json","graph_json":"https://pith.science/api/pith-number/MIY7RWZ24DGUFBYOL2MCO4KE73/graph.json","events_json":"https://pith.science/api/pith-number/MIY7RWZ24DGUFBYOL2MCO4KE73/events.json","paper":"https://pith.science/paper/MIY7RWZ2"},"agent_actions":{"view_html":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73","download_json":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73.json","view_paper":"https://pith.science/paper/MIY7RWZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18443&json=true","fetch_graph":"https://pith.science/api/pith-number/MIY7RWZ24DGUFBYOL2MCO4KE73/graph.json","fetch_events":"https://pith.science/api/pith-number/MIY7RWZ24DGUFBYOL2MCO4KE73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/action/storage_attestation","attest_author":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/action/author_attestation","sign_citation":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/action/citation_signature","submit_replication":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/action/replication_record"}},"created_at":"2026-07-05T09:15:31.861031+00:00","updated_at":"2026-07-05T09:15:31.861031+00:00"}