{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QQ2EMJDUAZDBNKFH3MCF63MRAL","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":"35737d9b7a247a1a7040de4dc5f4196dc7dea1a92a91296fc6fa546e480706c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T02:44:58Z","title_canon_sha256":"832d6013aad3935696d57f0484f51bb92a45e4fe5e0d6ae6abc1f8e7780ea488"},"schema_version":"1.0","source":{"id":"2506.19262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19262","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19262v2","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19262","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"pith_short_12","alias_value":"QQ2EMJDUAZDB","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"QQ2EMJDUAZDBNKFH","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"QQ2EMJDU","created_at":"2026-07-05T11:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:3564aa55a977054b8af88e547c3707aebaeb7a3c9c36affb35a85d415a7ac5fc","target":"graph","created_at":"2026-07-05T11:26:53Z","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/2506.19262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the remarkable generative capabilities of large language models (LLMs), using LLM-generated data to train downstream models has emerged as a promising approach to mitigate data scarcity in specific domains and reduce time-consuming annotations. However, recent studies have highlighted a critical issue: iterative training on self-generated data results in model collapse, where model performance degrades over time. Despite extensive research on the implications of LLM-generated data, these works often neglect the importance of data diversity, a key factor in data quality. In this work, we a","authors_text":"Haotong Wei, Huazhen Zhong, Liang Chen, Minghao Liu, Qunshu Lin, Xiaolong Sun, Yuchang Zhu, Zibin Zheng, Zixuan Yu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T02:44:58Z","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19262","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:df5920852308abc15e45458fa447f6d05815ef3bbc74e8249d68f8cc37ae58a9","target":"record","created_at":"2026-07-05T11:26:53Z","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":"35737d9b7a247a1a7040de4dc5f4196dc7dea1a92a91296fc6fa546e480706c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T02:44:58Z","title_canon_sha256":"832d6013aad3935696d57f0484f51bb92a45e4fe5e0d6ae6abc1f8e7780ea488"},"schema_version":"1.0","source":{"id":"2506.19262","kind":"arxiv","version":2}},"canonical_sha256":"8434462474064616a8a7db045f6d9102cb609212e130200e10dcd4de2921129c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8434462474064616a8a7db045f6d9102cb609212e130200e10dcd4de2921129c","first_computed_at":"2026-07-05T11:26:53.870639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:53.870639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PWGLk9ct8c1lZnLZh4MO3k6w9/ihxQuDhkalrw+ooDGM3iJ1fndSaprFchVfagKuOiELzYHGDhREUOzRtsFVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:53.871462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df5920852308abc15e45458fa447f6d05815ef3bbc74e8249d68f8cc37ae58a9","sha256:3564aa55a977054b8af88e547c3707aebaeb7a3c9c36affb35a85d415a7ac5fc"],"state_sha256":"73df60890c7ec0586bbda7a9fdc822c7c4b633f98d056983073698cd5437dc09"}