{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M5NJK4ICS7M3MF4GV6AEN5EELH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"31751731b7c302cdc44fcd380f7565990cf834db2a0e6c47b9aeb1dfddee0a29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T00:16:57Z","title_canon_sha256":"e28a11dc6051a22e6bd6693044c2a7395178ed0cad73215cf7c4a597245ef72c"},"schema_version":"1.0","source":{"id":"2501.11199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11199","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11199v2","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11199","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"M5NJK4ICS7M3","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"M5NJK4ICS7M3MF4G","created_at":"2026-07-05T10:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"M5NJK4IC","created_at":"2026-07-05T10:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:0437e00585f81d777ce7136962865c7b46e3973a4708af525cc5c76da9310ad7","target":"graph","created_at":"2026-07-05T10:05:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.11199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akshay Chaudhari, Fateme Nateghi Haredasht, Ivan Lopez, Jonathan H Chen, Kaitlin Caoili","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T00:16:57Z","title":"Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11199","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5c6a116d1b7f74954dff5b0d454edcc28ff1c6b0f61142b8c14c21105eec965","target":"record","created_at":"2026-07-05T10:05:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"31751731b7c302cdc44fcd380f7565990cf834db2a0e6c47b9aeb1dfddee0a29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T00:16:57Z","title_canon_sha256":"e28a11dc6051a22e6bd6693044c2a7395178ed0cad73215cf7c4a597245ef72c"},"schema_version":"1.0","source":{"id":"2501.11199","kind":"arxiv","version":2}},"canonical_sha256":"675a95710297d9b61786af8046f48459c8515afddf70f474ae2f6c7951bab4db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"675a95710297d9b61786af8046f48459c8515afddf70f474ae2f6c7951bab4db","first_computed_at":"2026-07-05T10:05:16.866093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:16.866093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gX9kS+RRgKnG3smdyBy0Jto7ckTD5+t234U2hClifPWqmS8LGQ8pfue3dxtbUzpevQwZidEJIHlq25yA3IpTCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:16.866592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5c6a116d1b7f74954dff5b0d454edcc28ff1c6b0f61142b8c14c21105eec965","sha256:0437e00585f81d777ce7136962865c7b46e3973a4708af525cc5c76da9310ad7"],"state_sha256":"9e578c5b998f5c6050f1ec7676868deff9bd5ff88950c20aa08bd816f4a34bf7"}