{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JSVLEIM4VDUNORTHMXEQXMJI2M","short_pith_number":"pith:JSVLEIM4","schema_version":"1.0","canonical_sha256":"4caab2219ca8e8d7466765c90bb128d318e5206192c8b9d7aec918393b7be47c","source":{"kind":"arxiv","id":"2310.00429","version":5},"attestation_state":"computed","paper":{"title":"On the Stability of Iterative Retraining of Generative Models on their own Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Duplessis, Avishek Joey Bose, Gauthier Gidel, Marco Jiralerspong, Quentin Bertrand","submitted_at":"2023-09-30T16:41:04Z","abstract_excerpt":"Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical human's ability to discern the authenticity of samples. Undeniably, a key driver of this success is enabled by the massive amounts of web-scale data consumed by these models. Due to these models' striking performance and ease of availability, the web will inevitably be increasingly populated with synthetic content. Such a fact directly implies that future iterations of generative models will be trained on both clean and artificially generated data from pas"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.00429","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-30T16:41:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5cf4063e47a4f7dfde19c6710f10957d92b7c71a87161023eafd0c2d139dc054","abstract_canon_sha256":"3e91de1ba5061c658f0d76c578efbe60f775062712a3f07dfa0fb7352ce4fd1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:26.775893Z","signature_b64":"EXiFMeGXEhv65PW9V4URf8iR95kFemrSlNydA/COQosApkVEbH3DmoBuAZQwOi/L4ugxD98t1v/srmTUSQH1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4caab2219ca8e8d7466765c90bb128d318e5206192c8b9d7aec918393b7be47c","last_reissued_at":"2026-07-05T08:03:26.775415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:26.775415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Stability of Iterative Retraining of Generative Models on their own Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Duplessis, Avishek Joey Bose, Gauthier Gidel, Marco Jiralerspong, Quentin Bertrand","submitted_at":"2023-09-30T16:41:04Z","abstract_excerpt":"Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical human's ability to discern the authenticity of samples. Undeniably, a key driver of this success is enabled by the massive amounts of web-scale data consumed by these models. Due to these models' striking performance and ease of availability, the web will inevitably be increasingly populated with synthetic content. Such a fact directly implies that future iterations of generative models will be trained on both clean and artificially generated data from pas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00429","kind":"arxiv","version":5},"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/2310.00429/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.00429","created_at":"2026-07-05T08:03:26.775466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00429v5","created_at":"2026-07-05T08:03:26.775466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00429","created_at":"2026-07-05T08:03:26.775466+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSVLEIM4VDUN","created_at":"2026-07-05T08:03:26.775466+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSVLEIM4VDUNORTH","created_at":"2026-07-05T08:03:26.775466+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSVLEIM4","created_at":"2026-07-05T08:03:26.775466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":128,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M","json":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M.json","graph_json":"https://pith.science/api/pith-number/JSVLEIM4VDUNORTHMXEQXMJI2M/graph.json","events_json":"https://pith.science/api/pith-number/JSVLEIM4VDUNORTHMXEQXMJI2M/events.json","paper":"https://pith.science/paper/JSVLEIM4"},"agent_actions":{"view_html":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M","download_json":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M.json","view_paper":"https://pith.science/paper/JSVLEIM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00429&json=true","fetch_graph":"https://pith.science/api/pith-number/JSVLEIM4VDUNORTHMXEQXMJI2M/graph.json","fetch_events":"https://pith.science/api/pith-number/JSVLEIM4VDUNORTHMXEQXMJI2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M/action/storage_attestation","attest_author":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M/action/author_attestation","sign_citation":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M/action/citation_signature","submit_replication":"https://pith.science/pith/JSVLEIM4VDUNORTHMXEQXMJI2M/action/replication_record"}},"created_at":"2026-07-05T08:03:26.775466+00:00","updated_at":"2026-07-05T08:03:26.775466+00:00"}