{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CU347JJNSNVJEWLSN5467RZVQE","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":"c5678275dab2612117be3f8a0f1e5bb098a4a8bbf351bf5ad74391d1760e57c9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T18:42:55Z","title_canon_sha256":"81ef85a9fc02d39a1291d9c5624dc13a552fba028d2e5bdab98515c2a4b24ffb"},"schema_version":"1.0","source":{"id":"2407.12835","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12835","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12835v2","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12835","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"CU347JJNSNVJ","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"CU347JJNSNVJEWLS","created_at":"2026-07-05T08:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"CU347JJN","created_at":"2026-07-05T08:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:54bc4f63db1a75be29e7dd38c88b287aaf52b6be16177d118bee179947f3672f","target":"graph","created_at":"2026-07-05T08:48:32Z","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/2407.12835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"What happens if we train a new Large Language Model (LLM) using data that are at least partially generated by other LLMs? The explosive success of LLMs means that a substantial amount of content online will be generated by LLMs rather than humans, which will inevitably enter the training datasets of next-generation LLMs. We evaluate the implications of such \"regurgitative training\" on LLM performance. Through fine-tuning GPT-3.5 with data generated either by itself or by other LLMs in a machine translation task, we find strong evidence that regurgitative training clearly handicaps the performa","authors_text":"Dandan Qiao, Jinghui Zhang, Mochen Yang, Qiang Wei","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T18:42:55Z","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12835","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":"sha256:94460da81027ad5d1700f35d55738a505e5b263f9e937c9e7831d9396a9d3fe5","target":"record","created_at":"2026-07-05T08:48:32Z","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":"c5678275dab2612117be3f8a0f1e5bb098a4a8bbf351bf5ad74391d1760e57c9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T18:42:55Z","title_canon_sha256":"81ef85a9fc02d39a1291d9c5624dc13a552fba028d2e5bdab98515c2a4b24ffb"},"schema_version":"1.0","source":{"id":"2407.12835","kind":"arxiv","version":2}},"canonical_sha256":"1537cfa52d936a9259726f79efc7358108614c57ac71fc25670ba09cf562dd99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1537cfa52d936a9259726f79efc7358108614c57ac71fc25670ba09cf562dd99","first_computed_at":"2026-07-05T08:48:32.447693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:32.447693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xq+qzf5sfQlExKHI97F256KF0vCa4GaRcuXeJ20fUNFKiSXAkXvaB0Yt1jT1OhAOi4Evi8CthlkkNxw3ls1OCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:32.448170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12835","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94460da81027ad5d1700f35d55738a505e5b263f9e937c9e7831d9396a9d3fe5","sha256:54bc4f63db1a75be29e7dd38c88b287aaf52b6be16177d118bee179947f3672f"],"state_sha256":"a4ecfa09e9a500a701d28e74e7f8f1f718948c7dbcc65bfac6c1d50ab091e4d1"}