{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IBNWRTBGZCMTOMJ5O2U67BX2EM","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":"8c57cfbf9431e29cb3275dd3040705f8c603657ea11d99975494fdc22b9c515c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T05:49:24Z","title_canon_sha256":"a030a9130daceadc32aca50f50afa280954ff6ac4ce12854359ef27d93310d38"},"schema_version":"1.0","source":{"id":"2410.16713","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16713","created_at":"2026-07-05T10:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16713v4","created_at":"2026-07-05T10:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16713","created_at":"2026-07-05T10:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"IBNWRTBGZCMT","created_at":"2026-07-05T10:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"IBNWRTBGZCMTOMJ5","created_at":"2026-07-05T10:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"IBNWRTBG","created_at":"2026-07-05T10:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:44b83ab1574b659ad174de65978a6e9e6c2f9f9d018f449b4723a6f5ec85a4c6","target":"graph","created_at":"2026-07-05T10:33:06Z","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/2410.16713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"What happens when generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models? Some prior work warns of \"model collapse\" as the web is overwhelmed by synthetic data; other work suggests the problem can be contained (i.e. collapse can be avoided) by managing how available data are used in pretraining. In this paper, we report experiments on three ways of using data (training-workflows), across three generative model task-settings (multivariate Gaussian estimation, kernel density estimation, and language-model fine-tuning) to further confir","authors_text":"Apratim Dey, David L. Donoho, Joshua Kazdan, Matthias Gerstgrasser, Rafael Rafailov, Rylan Schaeffer, Sanmi Koyejo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T05:49:24Z","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16713","kind":"arxiv","version":4},"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":"sha256:3fba9b1ae059db50eaeafd32432c0a59ce5687555e69ce60cdb4541f169d5235","target":"record","created_at":"2026-07-05T10:33:06Z","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":"8c57cfbf9431e29cb3275dd3040705f8c603657ea11d99975494fdc22b9c515c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T05:49:24Z","title_canon_sha256":"a030a9130daceadc32aca50f50afa280954ff6ac4ce12854359ef27d93310d38"},"schema_version":"1.0","source":{"id":"2410.16713","kind":"arxiv","version":4}},"canonical_sha256":"405b68cc26c89937313d76a9ef86fa2333d3df6febd848b00cada4dce765cd22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"405b68cc26c89937313d76a9ef86fa2333d3df6febd848b00cada4dce765cd22","first_computed_at":"2026-07-05T10:33:06.025943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:06.025943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FPGYFRaM67yB2lhbA02lBqWHisWMYz/+jA3J0PGzxYsdrm6tj+RyyzeB1hPnktfVPw46k+LJrGv1A+m2hJP2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:06.026956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16713","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fba9b1ae059db50eaeafd32432c0a59ce5687555e69ce60cdb4541f169d5235","sha256:44b83ab1574b659ad174de65978a6e9e6c2f9f9d018f449b4723a6f5ec85a4c6"],"state_sha256":"d679a0cab21d833145cc0b3ea0c6309473d3edd678dad3eb4b884f73d1578c43"}