{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LRXTH7ZCDA7I6JMH53VQ6DUZVA","short_pith_number":"pith:LRXTH7ZC","canonical_record":{"source":{"id":"2410.12954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:43:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bc81dd743dc7020c15c331ade57db33e4ad33bacd535f7bef2a569c2f7ec91b","abstract_canon_sha256":"b44849244eeab52a11b4dd0bfe1890cf9f8f29f02bfd162000ae2fbf2a7670a2"},"schema_version":"1.0"},"canonical_sha256":"5c6f33ff22183e8f2587eeeb0f0e99a83b2100234a10643afc3a120cbede9a2d","source":{"kind":"arxiv","id":"2410.12954","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12954","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12954v2","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12954","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"pith_short_12","alias_value":"LRXTH7ZCDA7I","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"pith_short_16","alias_value":"LRXTH7ZCDA7I6JMH","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"pith_short_8","alias_value":"LRXTH7ZC","created_at":"2026-07-05T09:25:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LRXTH7ZCDA7I6JMH53VQ6DUZVA","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:43:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bc81dd743dc7020c15c331ade57db33e4ad33bacd535f7bef2a569c2f7ec91b","abstract_canon_sha256":"b44849244eeab52a11b4dd0bfe1890cf9f8f29f02bfd162000ae2fbf2a7670a2"},"schema_version":"1.0"},"canonical_sha256":"5c6f33ff22183e8f2587eeeb0f0e99a83b2100234a10643afc3a120cbede9a2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:48.214985Z","signature_b64":"6cMbjBcLiHyZLFJDcpdWVXYfx+IG6da+5oM2CZTlGY3B7ugQF89Bee7jfH74CLZq1fbLYuaAnqBEi6Z+J3tqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c6f33ff22183e8f2587eeeb0f0e99a83b2100234a10643afc3a120cbede9a2d","last_reissued_at":"2026-07-05T09:25:48.214453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:48.214453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12954","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":"2026-07-05T09:25:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7Sg5n65KJtRdsRxXbpEcuNc5sXwYG8faCjqd/UK+YZUqMo4j2nzeWwO+adS68PKPVt8zhTuigFRPI3+1lfuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:58:31.821399Z"},"content_sha256":"b5885bb5a723327370ba802b23a717de379cf65d72e1005beae9f794b878c76b","schema_version":"1.0","event_id":"sha256:b5885bb5a723327370ba802b23a717de379cf65d72e1005beae9f794b878c76b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LRXTH7ZCDA7I6JMH53VQ6DUZVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Borji","submitted_at":"2024-10-16T18:43:52Z","abstract_excerpt":"The study conducted by Shumailov et al. (2024) demonstrates that repeatedly training a generative model on synthetic data leads to model collapse. This finding has generated considerable interest and debate, particularly given that current models have nearly exhausted the available data. In this work, we investigate the effects of fitting a distribution (through Kernel Density Estimation, or KDE) or a model to the data, followed by repeated sampling from it. Our objective is to develop a theoretical understanding of the phenomenon observed by Shumailov et al. (2024). Our results indicate that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12954","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/2410.12954/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":"2026-07-05T09:25:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7k37DhvKnKfv2ijsEHiqu/jeXFl4VLW/EILALYl3t3LC9yOi3xxJIkGHVL41XagxOvD/A1DE1GEpUL/sMJF/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:58:31.821923Z"},"content_sha256":"be5d694531f0cab84c9640dcba2b7fda52d7ed8784c79b67055578a2628cae21","schema_version":"1.0","event_id":"sha256:be5d694531f0cab84c9640dcba2b7fda52d7ed8784c79b67055578a2628cae21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA/bundle.json","state_url":"https://pith.science/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA/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":"2026-08-09T00:58:31Z","links":{"resolver":"https://pith.science/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA","bundle":"https://pith.science/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA/bundle.json","state":"https://pith.science/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRXTH7ZCDA7I6JMH53VQ6DUZVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LRXTH7ZCDA7I6JMH53VQ6DUZVA","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":"b44849244eeab52a11b4dd0bfe1890cf9f8f29f02bfd162000ae2fbf2a7670a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:43:52Z","title_canon_sha256":"5bc81dd743dc7020c15c331ade57db33e4ad33bacd535f7bef2a569c2f7ec91b"},"schema_version":"1.0","source":{"id":"2410.12954","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12954","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12954v2","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12954","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"pith_short_12","alias_value":"LRXTH7ZCDA7I","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"pith_short_16","alias_value":"LRXTH7ZCDA7I6JMH","created_at":"2026-07-05T09:25:48Z"},{"alias_kind":"pith_short_8","alias_value":"LRXTH7ZC","created_at":"2026-07-05T09:25:48Z"}],"graph_snapshots":[{"event_id":"sha256:be5d694531f0cab84c9640dcba2b7fda52d7ed8784c79b67055578a2628cae21","target":"graph","created_at":"2026-07-05T09:25:48Z","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/2410.12954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The study conducted by Shumailov et al. (2024) demonstrates that repeatedly training a generative model on synthetic data leads to model collapse. This finding has generated considerable interest and debate, particularly given that current models have nearly exhausted the available data. In this work, we investigate the effects of fitting a distribution (through Kernel Density Estimation, or KDE) or a model to the data, followed by repeated sampling from it. Our objective is to develop a theoretical understanding of the phenomenon observed by Shumailov et al. (2024). Our results indicate that ","authors_text":"Ali Borji","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:43:52Z","title":"A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12954","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:b5885bb5a723327370ba802b23a717de379cf65d72e1005beae9f794b878c76b","target":"record","created_at":"2026-07-05T09:25:48Z","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":"b44849244eeab52a11b4dd0bfe1890cf9f8f29f02bfd162000ae2fbf2a7670a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T18:43:52Z","title_canon_sha256":"5bc81dd743dc7020c15c331ade57db33e4ad33bacd535f7bef2a569c2f7ec91b"},"schema_version":"1.0","source":{"id":"2410.12954","kind":"arxiv","version":2}},"canonical_sha256":"5c6f33ff22183e8f2587eeeb0f0e99a83b2100234a10643afc3a120cbede9a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c6f33ff22183e8f2587eeeb0f0e99a83b2100234a10643afc3a120cbede9a2d","first_computed_at":"2026-07-05T09:25:48.214453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:48.214453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6cMbjBcLiHyZLFJDcpdWVXYfx+IG6da+5oM2CZTlGY3B7ugQF89Bee7jfH74CLZq1fbLYuaAnqBEi6Z+J3tqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:48.214985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12954","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5885bb5a723327370ba802b23a717de379cf65d72e1005beae9f794b878c76b","sha256:be5d694531f0cab84c9640dcba2b7fda52d7ed8784c79b67055578a2628cae21"],"state_sha256":"665475bb6ddc18ded614d69db3c4b09e8fd084f05e83de294a325d313f23ff73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRVemo3iSfPuII/q0519/QjpZ1lLkZrKAxyEBCrfDR1OxnTVllc92YsUD6vkcIdjmmTL2cQUSPeC2JOthviFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:58:31.825412Z","bundle_sha256":"c96583badac1ac59f21e205f2cde63609ff2d3a916114131b2a9cff6a72cf73c"}}