{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M5NJK4ICS7M3MF4GV6AEN5EELH","short_pith_number":"pith:M5NJK4IC","schema_version":"1.0","canonical_sha256":"675a95710297d9b61786af8046f48459c8515afddf70f474ae2f6c7951bab4db","source":{"kind":"arxiv","id":"2501.11199","version":2},"attestation_state":"computed","paper":{"title":"Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Chaudhari, Fateme Nateghi Haredasht, Ivan Lopez, Jonathan H Chen, Kaitlin Caoili","submitted_at":"2025-01-20T00:16:57Z","abstract_excerpt":"Accurate classification of clinical text often requires fine-tuning pre-trained language models, a process that is costly and time-consuming due to the need for high-quality data and expert annotators. Synthetic data generation offers an alternative, though pre-trained models may not capture the syntactic diversity of clinical notes. We propose an embedding-driven approach that uses diversity sampling from a small set of real clinical notes to guide large language models in few-shot prompting, generating synthetic text that better reflects clinical syntax. We evaluated this method using the Ch"},"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":"2501.11199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T00:16:57Z","cross_cats_sorted":[],"title_canon_sha256":"e28a11dc6051a22e6bd6693044c2a7395178ed0cad73215cf7c4a597245ef72c","abstract_canon_sha256":"31751731b7c302cdc44fcd380f7565990cf834db2a0e6c47b9aeb1dfddee0a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:16.866592Z","signature_b64":"gX9kS+RRgKnG3smdyBy0Jto7ckTD5+t234U2hClifPWqmS8LGQ8pfue3dxtbUzpevQwZidEJIHlq25yA3IpTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675a95710297d9b61786af8046f48459c8515afddf70f474ae2f6c7951bab4db","last_reissued_at":"2026-07-05T10:05:16.866093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:16.866093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Chaudhari, Fateme Nateghi Haredasht, Ivan Lopez, Jonathan H Chen, Kaitlin Caoili","submitted_at":"2025-01-20T00:16:57Z","abstract_excerpt":"Accurate classification of clinical text often requires fine-tuning pre-trained language models, a process that is costly and time-consuming due to the need for high-quality data and expert annotators. Synthetic data generation offers an alternative, though pre-trained models may not capture the syntactic diversity of clinical notes. We propose an embedding-driven approach that uses diversity sampling from a small set of real clinical notes to guide large language models in few-shot prompting, generating synthetic text that better reflects clinical syntax. We evaluated this method using the Ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11199","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/2501.11199/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":"2501.11199","created_at":"2026-07-05T10:05:16.866152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11199v2","created_at":"2026-07-05T10:05:16.866152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11199","created_at":"2026-07-05T10:05:16.866152+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5NJK4ICS7M3","created_at":"2026-07-05T10:05:16.866152+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5NJK4ICS7M3MF4G","created_at":"2026-07-05T10:05:16.866152+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5NJK4IC","created_at":"2026-07-05T10:05:16.866152+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/M5NJK4ICS7M3MF4GV6AEN5EELH","json":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH.json","graph_json":"https://pith.science/api/pith-number/M5NJK4ICS7M3MF4GV6AEN5EELH/graph.json","events_json":"https://pith.science/api/pith-number/M5NJK4ICS7M3MF4GV6AEN5EELH/events.json","paper":"https://pith.science/paper/M5NJK4IC"},"agent_actions":{"view_html":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH","download_json":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH.json","view_paper":"https://pith.science/paper/M5NJK4IC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11199&json=true","fetch_graph":"https://pith.science/api/pith-number/M5NJK4ICS7M3MF4GV6AEN5EELH/graph.json","fetch_events":"https://pith.science/api/pith-number/M5NJK4ICS7M3MF4GV6AEN5EELH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH/action/storage_attestation","attest_author":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH/action/author_attestation","sign_citation":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH/action/citation_signature","submit_replication":"https://pith.science/pith/M5NJK4ICS7M3MF4GV6AEN5EELH/action/replication_record"}},"created_at":"2026-07-05T10:05:16.866152+00:00","updated_at":"2026-07-05T10:05:16.866152+00:00"}