{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YDJ2XWWTDX7XU5NG43HBEL6QIF","short_pith_number":"pith:YDJ2XWWT","canonical_record":{"source":{"id":"2603.11784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T10:44:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0a82030e20bc1168f15106815a8f4b065cfb3338deb1f92be9f28c6beb8f45a5","abstract_canon_sha256":"c1a9711d8f7151b6a9bf6a7fda800ea4b9bcb8e5476a567c28568fbd6d4d96a6"},"schema_version":"1.0"},"canonical_sha256":"c0d3abdad31dff7a75a6e6ce122fd041555ab5da60aed16fc032174c4492339d","source":{"kind":"arxiv","id":"2603.11784","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11784","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11784v2","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11784","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"YDJ2XWWTDX7X","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"YDJ2XWWTDX7XU5NG","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"YDJ2XWWT","created_at":"2026-07-07T02:18:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YDJ2XWWTDX7XU5NG43HBEL6QIF","target":"record","payload":{"canonical_record":{"source":{"id":"2603.11784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T10:44:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0a82030e20bc1168f15106815a8f4b065cfb3338deb1f92be9f28c6beb8f45a5","abstract_canon_sha256":"c1a9711d8f7151b6a9bf6a7fda800ea4b9bcb8e5476a567c28568fbd6d4d96a6"},"schema_version":"1.0"},"canonical_sha256":"c0d3abdad31dff7a75a6e6ce122fd041555ab5da60aed16fc032174c4492339d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:37.154936Z","signature_b64":"OXcAIKx1por9T2T64hA0ZOR1D9iGjtr9oi/c5Ndt2nK6RnR9SdtEtF1esAYxu2FW/ZWHypeHW7NjJ5S6RhzvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0d3abdad31dff7a75a6e6ce122fd041555ab5da60aed16fc032174c4492339d","last_reissued_at":"2026-07-07T02:18:37.153930Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:37.153930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.11784","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":"2026-07-07T02:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J4VEn10xzA99fdXN9tbkqHnNgQ/6N1Q6la4NsrbOBSaIdYf/m+Sn1bSQHGKf0IPR/DfdfXs1TSKDomkW0QxtBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:12:42.424303Z"},"content_sha256":"2d613f14a47545c07b4fb2d6dbdf7e0060bb052377ae04a1b600c72dadf89ad8","schema_version":"1.0","event_id":"sha256:2d613f14a47545c07b4fb2d6dbdf7e0060bb052377ae04a1b600c72dadf89ad8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YDJ2XWWTDX7XU5NG43HBEL6QIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Generation with Replay: A Learning-Theoretic View of Model Collapse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amartya Sanyal, Giorgio Racca, Michal Valko","submitted_at":"2026-03-12T10:44:17Z","abstract_excerpt":"As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same time, widespread LLM usage increases the volume of machine-generated content on the web; together, these trends raise the likelihood of generated text re-entering future training corpora, increasing the associated risk of performance degradation often called model collapse. In practice, model developers address this concern through data cleaning, watermarking, s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11784","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/2603.11784/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":"2026-07-07T02:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAxp/7I3YJmk+gpMP1Y6O9PXBkUhiKH6s/C92WY4OHLpkDYSPAdvPSFWJB2MP/NiBBthYAlWAEFODmUxEKSdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:12:42.425230Z"},"content_sha256":"139c801c2f187f8dba4eae6b94bd10d0addbec86f52b37dcc43fed16e90dbf34","schema_version":"1.0","event_id":"sha256:139c801c2f187f8dba4eae6b94bd10d0addbec86f52b37dcc43fed16e90dbf34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF/bundle.json","state_url":"https://pith.science/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF/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":"2026-08-09T20:12:42Z","links":{"resolver":"https://pith.science/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF","bundle":"https://pith.science/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF/bundle.json","state":"https://pith.science/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDJ2XWWTDX7XU5NG43HBEL6QIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YDJ2XWWTDX7XU5NG43HBEL6QIF","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":"c1a9711d8f7151b6a9bf6a7fda800ea4b9bcb8e5476a567c28568fbd6d4d96a6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T10:44:17Z","title_canon_sha256":"0a82030e20bc1168f15106815a8f4b065cfb3338deb1f92be9f28c6beb8f45a5"},"schema_version":"1.0","source":{"id":"2603.11784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11784","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11784v2","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11784","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"YDJ2XWWTDX7X","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"YDJ2XWWTDX7XU5NG","created_at":"2026-07-07T02:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"YDJ2XWWT","created_at":"2026-07-07T02:18:37Z"}],"graph_snapshots":[{"event_id":"sha256:139c801c2f187f8dba4eae6b94bd10d0addbec86f52b37dcc43fed16e90dbf34","target":"graph","created_at":"2026-07-07T02:18:37Z","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/2603.11784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same time, widespread LLM usage increases the volume of machine-generated content on the web; together, these trends raise the likelihood of generated text re-entering future training corpora, increasing the associated risk of performance degradation often called model collapse. In practice, model developers address this concern through data cleaning, watermarking, s","authors_text":"Amartya Sanyal, Giorgio Racca, Michal Valko","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T10:44:17Z","title":"Language Generation with Replay: A Learning-Theoretic View of Model Collapse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11784","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":"sha256:2d613f14a47545c07b4fb2d6dbdf7e0060bb052377ae04a1b600c72dadf89ad8","target":"record","created_at":"2026-07-07T02:18:37Z","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":"c1a9711d8f7151b6a9bf6a7fda800ea4b9bcb8e5476a567c28568fbd6d4d96a6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T10:44:17Z","title_canon_sha256":"0a82030e20bc1168f15106815a8f4b065cfb3338deb1f92be9f28c6beb8f45a5"},"schema_version":"1.0","source":{"id":"2603.11784","kind":"arxiv","version":2}},"canonical_sha256":"c0d3abdad31dff7a75a6e6ce122fd041555ab5da60aed16fc032174c4492339d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0d3abdad31dff7a75a6e6ce122fd041555ab5da60aed16fc032174c4492339d","first_computed_at":"2026-07-07T02:18:37.153930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:37.153930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXcAIKx1por9T2T64hA0ZOR1D9iGjtr9oi/c5Ndt2nK6RnR9SdtEtF1esAYxu2FW/ZWHypeHW7NjJ5S6RhzvBg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:37.154936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.11784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d613f14a47545c07b4fb2d6dbdf7e0060bb052377ae04a1b600c72dadf89ad8","sha256:139c801c2f187f8dba4eae6b94bd10d0addbec86f52b37dcc43fed16e90dbf34"],"state_sha256":"02f5483c5ea2d526dfd6c91465f39e4885a45b702f4817b87279391fd7d5e36f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbZvdGcKoDeGA+EliCNQuiVxNrN+jGvbzS8VgVGwfCBcHwatJA7DzXk3+g38a+Kdu+sNkH2YQIYsT0PgmDxuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:12:42.433223Z","bundle_sha256":"ebfa288fd1ae2d2fec101f25b91f830e2921ff0c8a1bbc6fbe97d9469d76693a"}}