{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MJ2RJBY5UCDXTHTUFS4I2S24LN","short_pith_number":"pith:MJ2RJBY5","schema_version":"1.0","canonical_sha256":"627514871da087799e742cb88d4b5c5b632b1c6c3ae1979e7ec5d2ea8591d063","source":{"kind":"arxiv","id":"2508.08140","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Biomedical In-Context Learning: A Diversity-Enhanced Submodular Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Wang, Meijia Song, Mingquan Lin, Qixin Zhang, Rui Zhang, Zaifu Zhan","submitted_at":"2025-08-11T16:13:21Z","abstract_excerpt":"Recent progress in large language models (LLMs) has leveraged their in-context learning (ICL) abilities to enable quick adaptation to unseen biomedical NLP tasks. By incorporating only a few input-output examples into prompts, LLMs can rapidly perform these new tasks. While the impact of these demonstrations on LLM performance has been extensively studied, most existing approaches prioritize representativeness over diversity when selecting examples from large corpora. To address this gap, we propose Dual-Div, a diversity-enhanced data-efficient framework for demonstration selection in biomedic"},"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":"2508.08140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T16:13:21Z","cross_cats_sorted":[],"title_canon_sha256":"3902a3562440f975900e58fc64e3b53aff0cec8e17f8f59b2aae433be862b679","abstract_canon_sha256":"65a5f18b7bc306d74bf3964aa9d1332081f3e5568f7487fa3e346fc874131f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:08.915881Z","signature_b64":"h220ZiAL+5aFO6hqpQpQ0wx62EZ5/67/TLB/GMoSXfO4ZPoG/lChysGAfK0relNsBtBN1663wfVvRtgut0aLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"627514871da087799e742cb88d4b5c5b632b1c6c3ae1979e7ec5d2ea8591d063","last_reissued_at":"2026-07-05T11:52:08.915408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:08.915408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Biomedical In-Context Learning: A Diversity-Enhanced Submodular Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Wang, Meijia Song, Mingquan Lin, Qixin Zhang, Rui Zhang, Zaifu Zhan","submitted_at":"2025-08-11T16:13:21Z","abstract_excerpt":"Recent progress in large language models (LLMs) has leveraged their in-context learning (ICL) abilities to enable quick adaptation to unseen biomedical NLP tasks. By incorporating only a few input-output examples into prompts, LLMs can rapidly perform these new tasks. While the impact of these demonstrations on LLM performance has been extensively studied, most existing approaches prioritize representativeness over diversity when selecting examples from large corpora. To address this gap, we propose Dual-Div, a diversity-enhanced data-efficient framework for demonstration selection in biomedic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08140","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/2508.08140/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":"2508.08140","created_at":"2026-07-05T11:52:08.915465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08140v1","created_at":"2026-07-05T11:52:08.915465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08140","created_at":"2026-07-05T11:52:08.915465+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJ2RJBY5UCDX","created_at":"2026-07-05T11:52:08.915465+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJ2RJBY5UCDXTHTU","created_at":"2026-07-05T11:52:08.915465+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJ2RJBY5","created_at":"2026-07-05T11:52:08.915465+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/MJ2RJBY5UCDXTHTUFS4I2S24LN","json":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN.json","graph_json":"https://pith.science/api/pith-number/MJ2RJBY5UCDXTHTUFS4I2S24LN/graph.json","events_json":"https://pith.science/api/pith-number/MJ2RJBY5UCDXTHTUFS4I2S24LN/events.json","paper":"https://pith.science/paper/MJ2RJBY5"},"agent_actions":{"view_html":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN","download_json":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN.json","view_paper":"https://pith.science/paper/MJ2RJBY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08140&json=true","fetch_graph":"https://pith.science/api/pith-number/MJ2RJBY5UCDXTHTUFS4I2S24LN/graph.json","fetch_events":"https://pith.science/api/pith-number/MJ2RJBY5UCDXTHTUFS4I2S24LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN/action/storage_attestation","attest_author":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN/action/author_attestation","sign_citation":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN/action/citation_signature","submit_replication":"https://pith.science/pith/MJ2RJBY5UCDXTHTUFS4I2S24LN/action/replication_record"}},"created_at":"2026-07-05T11:52:08.915465+00:00","updated_at":"2026-07-05T11:52:08.915465+00:00"}