{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:62JL6FYCFWPEBPXDHYXIJA6K5D","short_pith_number":"pith:62JL6FYC","canonical_record":{"source":{"id":"2404.05090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T22:15:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"50e8021654e9a9f3296e63e7c76c9a90d373c101a8caa461205a5baf2b9d516f","abstract_canon_sha256":"5ec5d71756a01f2164e61ce77f93cda1b4cc7f815cbe324da7c1108b1fb95009"},"schema_version":"1.0"},"canonical_sha256":"f692bf17022d9e40bee33e2e8483cae8f803813ee930430aa4072c035001e7f3","source":{"kind":"arxiv","id":"2404.05090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05090","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05090v1","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05090","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"62JL6FYCFWPE","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"62JL6FYCFWPEBPXD","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"62JL6FYC","created_at":"2026-07-05T08:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:62JL6FYCFWPEBPXDHYXIJA6K5D","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T22:15:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"50e8021654e9a9f3296e63e7c76c9a90d373c101a8caa461205a5baf2b9d516f","abstract_canon_sha256":"5ec5d71756a01f2164e61ce77f93cda1b4cc7f815cbe324da7c1108b1fb95009"},"schema_version":"1.0"},"canonical_sha256":"f692bf17022d9e40bee33e2e8483cae8f803813ee930430aa4072c035001e7f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:26.015035Z","signature_b64":"o67C4Z0k0ZFLqMlKn12d/E/djEx0ajbTOQNP1ZfukHmkZ1XC2/q9QAtEMsCUR5ejSZObOUXgnSyvn7saJ3c0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f692bf17022d9e40bee33e2e8483cae8f803813ee930430aa4072c035001e7f3","last_reissued_at":"2026-07-05T08:05:26.014561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:26.014561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05090","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZHy0VdswE2U+hlcib4SZxhuZiR3gR9Xd15xeACLqM6FNbOEoO4XPlAqlsfjd7BnEdTZ42ERzatH6uGGmH+rCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:52:30.836103Z"},"content_sha256":"5359afda795456083da6855b4af2b56f2e489595b0b057b4e12d58f6f80a036c","schema_version":"1.0","event_id":"sha256:5359afda795456083da6855b4af2b56f2e489595b0b057b4e12d58f6f80a036c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:62JL6FYCFWPEBPXDHYXIJA6K5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Merouane Debbah, Mohamed El Amine Seddik, Pierre Youssef, Soufiane Hayou, Suei-Wen Chen","submitted_at":"2024-04-07T22:15:13Z","abstract_excerpt":"The phenomenon of model collapse, introduced in (Shumailov et al., 2023), refers to the deterioration in performance that occurs when new models are trained on synthetic data generated from previously trained models. This recursive training loop makes the tails of the original distribution disappear, thereby making future-generation models forget about the initial (real) distribution. With the aim of rigorously understanding model collapse in language models, we consider in this paper a statistical model that allows us to characterize the impact of various recursive training scenarios. Specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05090","kind":"arxiv","version":1},"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/2404.05090/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":"2026-07-05T08:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1L2ZnJHkcaOCynYJMPpisSr28KlZEzinvVi6ERJDUk3ehZdk0uyYIUj3reSg4KQe28pWm2kvqrnp2BpYfGKUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:52:30.837057Z"},"content_sha256":"236eb1a7982c4b580800656042714670a3c9b3a2fa70d37a9d36879e8f49ee72","schema_version":"1.0","event_id":"sha256:236eb1a7982c4b580800656042714670a3c9b3a2fa70d37a9d36879e8f49ee72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62JL6FYCFWPEBPXDHYXIJA6K5D/bundle.json","state_url":"https://pith.science/pith/62JL6FYCFWPEBPXDHYXIJA6K5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62JL6FYCFWPEBPXDHYXIJA6K5D/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":"2026-08-11T16:52:30Z","links":{"resolver":"https://pith.science/pith/62JL6FYCFWPEBPXDHYXIJA6K5D","bundle":"https://pith.science/pith/62JL6FYCFWPEBPXDHYXIJA6K5D/bundle.json","state":"https://pith.science/pith/62JL6FYCFWPEBPXDHYXIJA6K5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62JL6FYCFWPEBPXDHYXIJA6K5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:62JL6FYCFWPEBPXDHYXIJA6K5D","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":"5ec5d71756a01f2164e61ce77f93cda1b4cc7f815cbe324da7c1108b1fb95009","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T22:15:13Z","title_canon_sha256":"50e8021654e9a9f3296e63e7c76c9a90d373c101a8caa461205a5baf2b9d516f"},"schema_version":"1.0","source":{"id":"2404.05090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05090","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05090v1","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05090","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"62JL6FYCFWPE","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"62JL6FYCFWPEBPXD","created_at":"2026-07-05T08:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"62JL6FYC","created_at":"2026-07-05T08:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:236eb1a7982c4b580800656042714670a3c9b3a2fa70d37a9d36879e8f49ee72","target":"graph","created_at":"2026-07-05T08:05:26Z","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/2404.05090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The phenomenon of model collapse, introduced in (Shumailov et al., 2023), refers to the deterioration in performance that occurs when new models are trained on synthetic data generated from previously trained models. This recursive training loop makes the tails of the original distribution disappear, thereby making future-generation models forget about the initial (real) distribution. With the aim of rigorously understanding model collapse in language models, we consider in this paper a statistical model that allows us to characterize the impact of various recursive training scenarios. Specifi","authors_text":"Merouane Debbah, Mohamed El Amine Seddik, Pierre Youssef, Soufiane Hayou, Suei-Wen Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T22:15:13Z","title":"How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05090","kind":"arxiv","version":1},"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":"sha256:5359afda795456083da6855b4af2b56f2e489595b0b057b4e12d58f6f80a036c","target":"record","created_at":"2026-07-05T08:05:26Z","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":"5ec5d71756a01f2164e61ce77f93cda1b4cc7f815cbe324da7c1108b1fb95009","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T22:15:13Z","title_canon_sha256":"50e8021654e9a9f3296e63e7c76c9a90d373c101a8caa461205a5baf2b9d516f"},"schema_version":"1.0","source":{"id":"2404.05090","kind":"arxiv","version":1}},"canonical_sha256":"f692bf17022d9e40bee33e2e8483cae8f803813ee930430aa4072c035001e7f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f692bf17022d9e40bee33e2e8483cae8f803813ee930430aa4072c035001e7f3","first_computed_at":"2026-07-05T08:05:26.014561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:26.014561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o67C4Z0k0ZFLqMlKn12d/E/djEx0ajbTOQNP1ZfukHmkZ1XC2/q9QAtEMsCUR5ejSZObOUXgnSyvn7saJ3c0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:26.015035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5359afda795456083da6855b4af2b56f2e489595b0b057b4e12d58f6f80a036c","sha256:236eb1a7982c4b580800656042714670a3c9b3a2fa70d37a9d36879e8f49ee72"],"state_sha256":"b50b6fc0d870d80ec570976b5b2c789c671afb378ec961db6ae4b58136a68a3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"daRN468Y8uX4co6oL9y3KxpgB/x2ZZN/DIzoB5wSFQLmNGWeQBursbWo461WWGbddkLdfB+eQq3/V3uIKp1FCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:52:30.843027Z","bundle_sha256":"8ac0300465b7c41a6465f95de6634ea72f0ca1c5b8cd6306747097d3eb119f3d"}}