{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z2NJ3VBQYW5HVO62DC2AKH2HAQ","short_pith_number":"pith:Z2NJ3VBQ","schema_version":"1.0","canonical_sha256":"ce9a9dd430c5ba7abbda18b4051f4704057cc4e72c1a9c497dee7452463b6d52","source":{"kind":"arxiv","id":"2502.08661","version":2},"attestation_state":"computed","paper":{"title":"Few-shot LLM Synthetic Data with Distribution Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuhan Wu, Jiyuan Ren, Qinglin Jia, Sunhao Dai, Zhaocheng Du, Zhenhua Dong, Zhihao Wen","submitted_at":"2025-02-09T16:43:32Z","abstract_excerpt":"As large language models (LLMs) advance, their ability to perform in-context learning and few-shot language generation has improved significantly. This has spurred using LLMs to produce high-quality synthetic data to enhance the performance of smaller models like online retrievers or weak LLMs. However, LLM-generated synthetic data often differs from the real data in key language attributes (e.g., styles, tones, content proportions, etc.). As a result, mixing these synthetic data directly with real data may distort the original data distribution, potentially hindering performance improvements."},"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":"2502.08661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T16:43:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef651004480664d15d280d9729354cd0c400118ab30e2d64cefb58701bd521f7","abstract_canon_sha256":"ce8c15c9c686355b2a65a87fca1a8c25645f577eb6b4e66e6cc5c4fc5e311870"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:51.348882Z","signature_b64":"PSNJsnGredcSZjgBg83jL0UsgqjkHzvKfmY8zDE9uVpa73WtVM+k2yJ74bzGf4Rwr7bgI0PLxAlC2uJdZFLuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce9a9dd430c5ba7abbda18b4051f4704057cc4e72c1a9c497dee7452463b6d52","last_reissued_at":"2026-07-05T10:14:51.348357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:51.348357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-shot LLM Synthetic Data with Distribution Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuhan Wu, Jiyuan Ren, Qinglin Jia, Sunhao Dai, Zhaocheng Du, Zhenhua Dong, Zhihao Wen","submitted_at":"2025-02-09T16:43:32Z","abstract_excerpt":"As large language models (LLMs) advance, their ability to perform in-context learning and few-shot language generation has improved significantly. This has spurred using LLMs to produce high-quality synthetic data to enhance the performance of smaller models like online retrievers or weak LLMs. However, LLM-generated synthetic data often differs from the real data in key language attributes (e.g., styles, tones, content proportions, etc.). As a result, mixing these synthetic data directly with real data may distort the original data distribution, potentially hindering performance improvements."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08661","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/2502.08661/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":"2502.08661","created_at":"2026-07-05T10:14:51.348424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08661v2","created_at":"2026-07-05T10:14:51.348424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08661","created_at":"2026-07-05T10:14:51.348424+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2NJ3VBQYW5H","created_at":"2026-07-05T10:14:51.348424+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2NJ3VBQYW5HVO62","created_at":"2026-07-05T10:14:51.348424+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2NJ3VBQ","created_at":"2026-07-05T10:14:51.348424+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/Z2NJ3VBQYW5HVO62DC2AKH2HAQ","json":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ.json","graph_json":"https://pith.science/api/pith-number/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/graph.json","events_json":"https://pith.science/api/pith-number/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/events.json","paper":"https://pith.science/paper/Z2NJ3VBQ"},"agent_actions":{"view_html":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ","download_json":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ.json","view_paper":"https://pith.science/paper/Z2NJ3VBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08661&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/action/storage_attestation","attest_author":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/action/author_attestation","sign_citation":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/action/citation_signature","submit_replication":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/action/replication_record"}},"created_at":"2026-07-05T10:14:51.348424+00:00","updated_at":"2026-07-05T10:14:51.348424+00:00"}