{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O6VCMG3JJEGSKN4FL4VGRK4PGM","short_pith_number":"pith:O6VCMG3J","canonical_record":{"source":{"id":"2406.12397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T08:38:59Z","cross_cats_sorted":[],"title_canon_sha256":"74e2a3639118672a40b5a4bcc31e79f887ad80ec6b1b8dedf21e5f9463f52a38","abstract_canon_sha256":"229a4e24c2a160ed76c6785687ffb65dc345176ee245563186e73ccb44914bfb"},"schema_version":"1.0"},"canonical_sha256":"77aa261b69490d2537855f2a68ab8f332a74bf3ecf6339146efdf630371011bf","source":{"kind":"arxiv","id":"2406.12397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12397","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12397v1","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12397","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"pith_short_12","alias_value":"O6VCMG3JJEGS","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"pith_short_16","alias_value":"O6VCMG3JJEGSKN4F","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"pith_short_8","alias_value":"O6VCMG3J","created_at":"2026-07-05T08:33:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O6VCMG3JJEGSKN4FL4VGRK4PGM","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T08:38:59Z","cross_cats_sorted":[],"title_canon_sha256":"74e2a3639118672a40b5a4bcc31e79f887ad80ec6b1b8dedf21e5f9463f52a38","abstract_canon_sha256":"229a4e24c2a160ed76c6785687ffb65dc345176ee245563186e73ccb44914bfb"},"schema_version":"1.0"},"canonical_sha256":"77aa261b69490d2537855f2a68ab8f332a74bf3ecf6339146efdf630371011bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:45.707518Z","signature_b64":"Ws3dbdeBVAb6ftu2FrfTfHdkdqpKKgOH4/zwq+V242mWYcX20eYx5i5rUX5O38ruVnkAhmZBaySNSMlKXjsDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77aa261b69490d2537855f2a68ab8f332a74bf3ecf6339146efdf630371011bf","last_reissued_at":"2026-07-05T08:33:45.707006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:45.707006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12397","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:33:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdKdQchJk/1i4Q9peUnviMtp0RQfl2/ovnb6hyW6Rin/SCtYDzLPkTntwftG1LTndBcLgbawU40KZdGXMfKUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:04:46.400598Z"},"content_sha256":"8c90ae0d2c0f295d406cb7f35b69117b765cc26c8f2a7e97c250622c58496380","schema_version":"1.0","event_id":"sha256:8c90ae0d2c0f295d406cb7f35b69117b765cc26c8f2a7e97c250622c58496380"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O6VCMG3JJEGSKN4FL4VGRK4PGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingning Wang, Jie Chen, Ji-Rong Wen, Wayne Xin Zhao, Weipeng Chen, Yupeng Zhang","submitted_at":"2024-06-18T08:38:59Z","abstract_excerpt":"Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on downstream benchmarks. However, despite its potential benefits, our analysis suggests that there may be inherent flaws in synthetic data. The uniform format of synthetic data can lead to pattern overfitting and cause significant shifts in the output distribution, thereby reducing the model's instruction-following capabilities. Our work delves into these specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12397","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/2406.12397/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":"2026-07-05T08:33:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EXRtEsfSpLn4f/PToJ8KQqki0b69MRLjHD4bB2ZiU4RbxG4/M8WHYCufnpmn26T1ikDT8dfsZkMKIikOPeBAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:04:46.401601Z"},"content_sha256":"55f3387e39f45be20f20107b7fc8b7f29f2b91c22445c24ca2895f767a0395f8","schema_version":"1.0","event_id":"sha256:55f3387e39f45be20f20107b7fc8b7f29f2b91c22445c24ca2895f767a0395f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM/bundle.json","state_url":"https://pith.science/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM/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":"2026-08-18T14:04:46Z","links":{"resolver":"https://pith.science/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM","bundle":"https://pith.science/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM/bundle.json","state":"https://pith.science/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6VCMG3JJEGSKN4FL4VGRK4PGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O6VCMG3JJEGSKN4FL4VGRK4PGM","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":"229a4e24c2a160ed76c6785687ffb65dc345176ee245563186e73ccb44914bfb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T08:38:59Z","title_canon_sha256":"74e2a3639118672a40b5a4bcc31e79f887ad80ec6b1b8dedf21e5f9463f52a38"},"schema_version":"1.0","source":{"id":"2406.12397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12397","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12397v1","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12397","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"pith_short_12","alias_value":"O6VCMG3JJEGS","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"pith_short_16","alias_value":"O6VCMG3JJEGSKN4F","created_at":"2026-07-05T08:33:45Z"},{"alias_kind":"pith_short_8","alias_value":"O6VCMG3J","created_at":"2026-07-05T08:33:45Z"}],"graph_snapshots":[{"event_id":"sha256:55f3387e39f45be20f20107b7fc8b7f29f2b91c22445c24ca2895f767a0395f8","target":"graph","created_at":"2026-07-05T08:33:45Z","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/2406.12397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on downstream benchmarks. However, despite its potential benefits, our analysis suggests that there may be inherent flaws in synthetic data. The uniform format of synthetic data can lead to pattern overfitting and cause significant shifts in the output distribution, thereby reducing the model's instruction-following capabilities. Our work delves into these specifi","authors_text":"Bingning Wang, Jie Chen, Ji-Rong Wen, Wayne Xin Zhao, Weipeng Chen, Yupeng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T08:38:59Z","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12397","kind":"arxiv","version":1},"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":"sha256:8c90ae0d2c0f295d406cb7f35b69117b765cc26c8f2a7e97c250622c58496380","target":"record","created_at":"2026-07-05T08:33:45Z","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":"229a4e24c2a160ed76c6785687ffb65dc345176ee245563186e73ccb44914bfb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T08:38:59Z","title_canon_sha256":"74e2a3639118672a40b5a4bcc31e79f887ad80ec6b1b8dedf21e5f9463f52a38"},"schema_version":"1.0","source":{"id":"2406.12397","kind":"arxiv","version":1}},"canonical_sha256":"77aa261b69490d2537855f2a68ab8f332a74bf3ecf6339146efdf630371011bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77aa261b69490d2537855f2a68ab8f332a74bf3ecf6339146efdf630371011bf","first_computed_at":"2026-07-05T08:33:45.707006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:45.707006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ws3dbdeBVAb6ftu2FrfTfHdkdqpKKgOH4/zwq+V242mWYcX20eYx5i5rUX5O38ruVnkAhmZBaySNSMlKXjsDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:45.707518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c90ae0d2c0f295d406cb7f35b69117b765cc26c8f2a7e97c250622c58496380","sha256:55f3387e39f45be20f20107b7fc8b7f29f2b91c22445c24ca2895f767a0395f8"],"state_sha256":"a245c060ba324399ccf5e99b66fd58d5f3c00f55c2c69755e905897718c3b0b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Saw1mLZhXwVV75J2+bmcCw+wB+amyUQ3mBf3uBJcgVxgBNjae4BGGX+BdLHv6fxV5OTjqS6VyT/0kG8CLA0rAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:04:46.407380Z","bundle_sha256":"342891de05ad1f2d22e1014f159e96bece28e03d60f6851da93ae95b8ace800b"}}