{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z2NJ3VBQYW5HVO62DC2AKH2HAQ","short_pith_number":"pith:Z2NJ3VBQ","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"},"canonical_sha256":"ce9a9dd430c5ba7abbda18b4051f4704057cc4e72c1a9c497dee7452463b6d52","source":{"kind":"arxiv","id":"2502.08661","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08661","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08661v2","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08661","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"Z2NJ3VBQYW5H","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"Z2NJ3VBQYW5HVO62","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"Z2NJ3VBQ","created_at":"2026-07-05T10:14:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z2NJ3VBQYW5HVO62DC2AKH2HAQ","target":"record","payload":{"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"},"canonical_sha256":"ce9a9dd430c5ba7abbda18b4051f4704057cc4e72c1a9c497dee7452463b6d52","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"},"source_kind":"arxiv","source_id":"2502.08661","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1FwJcI5WaQPtG6mbU60xRreiU9gOrDp/68q3sKccRLIsDqkDYWY+EyWChbibpH56Bftll+4KdxDRDSOEghyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:31:12.979289Z"},"content_sha256":"1aeed72374f445c5de158a0ffd29e4bf5ce8d273d45b80f1027331fd687dc85f","schema_version":"1.0","event_id":"sha256:1aeed72374f445c5de158a0ffd29e4bf5ce8d273d45b80f1027331fd687dc85f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z2NJ3VBQYW5HVO62DC2AKH2HAQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNIryeRePpbvVGONz+6Ix92eLSPbCK+Xm9z4dZyyUAlBJfH8MMDQpUqa0GJU+migNpTwlIlyheOR25gKmnOgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:31:12.980084Z"},"content_sha256":"a37429bcb519b1b1a237b1a4c22ee576f7c277ab79dc2b66d4b0fb09d53d2d66","schema_version":"1.0","event_id":"sha256:a37429bcb519b1b1a237b1a4c22ee576f7c277ab79dc2b66d4b0fb09d53d2d66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/bundle.json","state_url":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T23:31:12Z","links":{"resolver":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ","bundle":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/bundle.json","state":"https://pith.science/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2NJ3VBQYW5HVO62DC2AKH2HAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z2NJ3VBQYW5HVO62DC2AKH2HAQ","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":"ce8c15c9c686355b2a65a87fca1a8c25645f577eb6b4e66e6cc5c4fc5e311870","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T16:43:32Z","title_canon_sha256":"ef651004480664d15d280d9729354cd0c400118ab30e2d64cefb58701bd521f7"},"schema_version":"1.0","source":{"id":"2502.08661","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08661","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08661v2","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08661","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"Z2NJ3VBQYW5H","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"Z2NJ3VBQYW5HVO62","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"Z2NJ3VBQ","created_at":"2026-07-05T10:14:51Z"}],"graph_snapshots":[{"event_id":"sha256:a37429bcb519b1b1a237b1a4c22ee576f7c277ab79dc2b66d4b0fb09d53d2d66","target":"graph","created_at":"2026-07-05T10:14:51Z","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/2502.08661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Chuhan Wu, Jiyuan Ren, Qinglin Jia, Sunhao Dai, Zhaocheng Du, Zhenhua Dong, Zhihao Wen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T16:43:32Z","title":"Few-shot LLM Synthetic Data with Distribution Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08661","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":"sha256:1aeed72374f445c5de158a0ffd29e4bf5ce8d273d45b80f1027331fd687dc85f","target":"record","created_at":"2026-07-05T10:14:51Z","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":"ce8c15c9c686355b2a65a87fca1a8c25645f577eb6b4e66e6cc5c4fc5e311870","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T16:43:32Z","title_canon_sha256":"ef651004480664d15d280d9729354cd0c400118ab30e2d64cefb58701bd521f7"},"schema_version":"1.0","source":{"id":"2502.08661","kind":"arxiv","version":2}},"canonical_sha256":"ce9a9dd430c5ba7abbda18b4051f4704057cc4e72c1a9c497dee7452463b6d52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce9a9dd430c5ba7abbda18b4051f4704057cc4e72c1a9c497dee7452463b6d52","first_computed_at":"2026-07-05T10:14:51.348357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:51.348357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PSNJsnGredcSZjgBg83jL0UsgqjkHzvKfmY8zDE9uVpa73WtVM+k2yJ74bzGf4Rwr7bgI0PLxAlC2uJdZFLuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:51.348882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08661","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aeed72374f445c5de158a0ffd29e4bf5ce8d273d45b80f1027331fd687dc85f","sha256:a37429bcb519b1b1a237b1a4c22ee576f7c277ab79dc2b66d4b0fb09d53d2d66"],"state_sha256":"4caf037e6248e108ff1877af29b6a3c54f605f89799e7dc18625eb6494a401a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jyUx5Vbl7xYMLFzoVqhhBDcXVFNA5K3+elUmXXIcHp4nfBCpnZG2Rfn6X5gV9WHEgtqJ8RE5BtZlWDcgcouxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:31:12.986133Z","bundle_sha256":"b8aaf98b350b97ef1123b510a0e72f8cc3cf88c27fd4c30e6400090b6f93fe91"}}