{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MBVNKNOFALFZD3TSFMXKMYGWZD","short_pith_number":"pith:MBVNKNOF","canonical_record":{"source":{"id":"2402.11778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T02:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78048b46fda849a2c3fd9e7ae8bdca3200dccf977d1f25aae4211d0f8b24ca92","abstract_canon_sha256":"cb57d046f12071eda86dc69ce985b695a5965981810fb0b2043e2706b6caf9a6"},"schema_version":"1.0"},"canonical_sha256":"606ad535c502cb91ee722b2ea660d6c8e2cdc0370b43ff8ac2961694f1af5caa","source":{"kind":"arxiv","id":"2402.11778","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11778","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11778v2","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11778","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"MBVNKNOFALFZ","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"MBVNKNOFALFZD3TS","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"MBVNKNOF","created_at":"2026-07-05T08:35:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MBVNKNOFALFZD3TSFMXKMYGWZD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T02:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78048b46fda849a2c3fd9e7ae8bdca3200dccf977d1f25aae4211d0f8b24ca92","abstract_canon_sha256":"cb57d046f12071eda86dc69ce985b695a5965981810fb0b2043e2706b6caf9a6"},"schema_version":"1.0"},"canonical_sha256":"606ad535c502cb91ee722b2ea660d6c8e2cdc0370b43ff8ac2961694f1af5caa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:42.070256Z","signature_b64":"URB5XnpL7j1+zmM+vxAFujVTKCkvOtv0YRqAHYSNsSfl53kceVcoFGwBdY05+28shRCCFOfzaN5dlpw8u0OtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606ad535c502cb91ee722b2ea660d6c8e2cdc0370b43ff8ac2961694f1af5caa","last_reissued_at":"2026-07-05T08:35:42.069802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:42.069802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11778","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HK+Z63cCxiVr1QVIB0NESDOUZcCHhdkkUleiYj4OHiuyWOrku3rX+qz7GqjXcc9NVYQxAEnUc40LLpwPHcXKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:09:31.081489Z"},"content_sha256":"60e4a13eb2bc8d3be39cc3ec8bd7926a9873791a6a765871b4489875e64b3c0e","schema_version":"1.0","event_id":"sha256:60e4a13eb2bc8d3be39cc3ec8bd7926a9873791a6a765871b4489875e64b3c0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MBVNKNOFALFZD3TSFMXKMYGWZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Theoretical Understandings of Self-Consuming Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Sen Zhang, Shi Fu, Xinmei Tian, Yingjie Wang","submitted_at":"2024-02-19T02:08:09Z","abstract_excerpt":"This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models, including parametric and non-parametric models. Specifically, we derive bounds on the total variation (TV) distance between the synthetic data distributions produced by future models and the original real data distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11778","kind":"arxiv","version":2},"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/2402.11778/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":"2026-07-05T08:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZ2rjvPkFQlq4HIL1B56vCFqv24Q6IAN4v6InofzWbpVVP3gzN1ay4W2uOka0pdQx+hh/2XmpOsflh0puzxIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:09:31.082350Z"},"content_sha256":"ea1c1efa88b98a343fedece7b7dfeca914df8552039a0698b044b616a55da69b","schema_version":"1.0","event_id":"sha256:ea1c1efa88b98a343fedece7b7dfeca914df8552039a0698b044b616a55da69b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBVNKNOFALFZD3TSFMXKMYGWZD/bundle.json","state_url":"https://pith.science/pith/MBVNKNOFALFZD3TSFMXKMYGWZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBVNKNOFALFZD3TSFMXKMYGWZD/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":"2026-08-04T09:09:31Z","links":{"resolver":"https://pith.science/pith/MBVNKNOFALFZD3TSFMXKMYGWZD","bundle":"https://pith.science/pith/MBVNKNOFALFZD3TSFMXKMYGWZD/bundle.json","state":"https://pith.science/pith/MBVNKNOFALFZD3TSFMXKMYGWZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBVNKNOFALFZD3TSFMXKMYGWZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MBVNKNOFALFZD3TSFMXKMYGWZD","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":"cb57d046f12071eda86dc69ce985b695a5965981810fb0b2043e2706b6caf9a6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T02:08:09Z","title_canon_sha256":"78048b46fda849a2c3fd9e7ae8bdca3200dccf977d1f25aae4211d0f8b24ca92"},"schema_version":"1.0","source":{"id":"2402.11778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11778","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11778v2","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11778","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"MBVNKNOFALFZ","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"MBVNKNOFALFZD3TS","created_at":"2026-07-05T08:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"MBVNKNOF","created_at":"2026-07-05T08:35:42Z"}],"graph_snapshots":[{"event_id":"sha256:ea1c1efa88b98a343fedece7b7dfeca914df8552039a0698b044b616a55da69b","target":"graph","created_at":"2026-07-05T08:35:42Z","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/2402.11778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models, including parametric and non-parametric models. Specifically, we derive bounds on the total variation (TV) distance between the synthetic data distributions produced by future models and the original real data distribution","authors_text":"Dacheng Tao, Sen Zhang, Shi Fu, Xinmei Tian, Yingjie Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T02:08:09Z","title":"Towards Theoretical Understandings of Self-Consuming Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11778","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":"sha256:60e4a13eb2bc8d3be39cc3ec8bd7926a9873791a6a765871b4489875e64b3c0e","target":"record","created_at":"2026-07-05T08:35:42Z","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":"cb57d046f12071eda86dc69ce985b695a5965981810fb0b2043e2706b6caf9a6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T02:08:09Z","title_canon_sha256":"78048b46fda849a2c3fd9e7ae8bdca3200dccf977d1f25aae4211d0f8b24ca92"},"schema_version":"1.0","source":{"id":"2402.11778","kind":"arxiv","version":2}},"canonical_sha256":"606ad535c502cb91ee722b2ea660d6c8e2cdc0370b43ff8ac2961694f1af5caa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"606ad535c502cb91ee722b2ea660d6c8e2cdc0370b43ff8ac2961694f1af5caa","first_computed_at":"2026-07-05T08:35:42.069802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:42.069802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"URB5XnpL7j1+zmM+vxAFujVTKCkvOtv0YRqAHYSNsSfl53kceVcoFGwBdY05+28shRCCFOfzaN5dlpw8u0OtDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:42.070256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60e4a13eb2bc8d3be39cc3ec8bd7926a9873791a6a765871b4489875e64b3c0e","sha256:ea1c1efa88b98a343fedece7b7dfeca914df8552039a0698b044b616a55da69b"],"state_sha256":"962a391c90fd99cc3a3fd1b3c9a9e257e0e3b518f85b1c38ef08e923ff12f6c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"muZ1s7jkTSPITu/YJ8cgtJKiq0I8dcuutTGQdXcigCmJYAFKcskj4fDdwUcfg7jmSazWUZ/3LiKN66s76/10Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:09:31.090532Z","bundle_sha256":"b67dd69354df2143f58e71600ba857b5800778f4456f0da2b629d5606129c312"}}