{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VMFX7YHVPVDO7H7XUQUBKXHHKJ","short_pith_number":"pith:VMFX7YHV","canonical_record":{"source":{"id":"2412.14689","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T09:43:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"73ec5819b38d42cfe5fdf4a9e6abd6eda5d2251a93ed6d666bf1dac570984b9a","abstract_canon_sha256":"e91d91c0d6d8382420e94c820b98f689df9d007060b8f232ba5d9b7bf18913e8"},"schema_version":"1.0"},"canonical_sha256":"ab0b7fe0f57d46ef9ff7a428155ce75268787541e126c5bd8bc6742e02b8e062","source":{"kind":"arxiv","id":"2412.14689","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14689","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14689v3","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14689","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"VMFX7YHVPVDO","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"VMFX7YHVPVDO7H7X","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"VMFX7YHV","created_at":"2026-07-05T11:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VMFX7YHVPVDO7H7XUQUBKXHHKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14689","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T09:43:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"73ec5819b38d42cfe5fdf4a9e6abd6eda5d2251a93ed6d666bf1dac570984b9a","abstract_canon_sha256":"e91d91c0d6d8382420e94c820b98f689df9d007060b8f232ba5d9b7bf18913e8"},"schema_version":"1.0"},"canonical_sha256":"ab0b7fe0f57d46ef9ff7a428155ce75268787541e126c5bd8bc6742e02b8e062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:49.684745Z","signature_b64":"NGV9T8ftijDctcdjz6xrL2QhqgQJJ8unR09urw58c3oKFeMP0N5Md2HPhUP4JeKKMMQktqNQFl5gzYJ/FbG/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab0b7fe0f57d46ef9ff7a428155ce75268787541e126c5bd8bc6742e02b8e062","last_reissued_at":"2026-07-05T11:10:49.684185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:49.684185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14689","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ms96vE4oXylMG2NuU3drtzydkyjDhB6liLdGM78YpWMt0RxFLgDAI3mLSh9BXhiuWe2Z95OOXB7NGtwqUST5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:42:31.997710Z"},"content_sha256":"ef052af507a22c382f3cdd46ba83b108118f141ebd03c4c46e0aad44794ede30","schema_version":"1.0","event_id":"sha256:ef052af507a22c382f3cdd46ba83b108118f141ebd03c4c46e0aad44794ede30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VMFX7YHVPVDO7H7XUQUBKXHHKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Synthesize Text Data without Model Collapse?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Daixuan Cheng, Ermo Hua, Hengli Li, Kaiyan Zhang, Ning Ding, Xingtai Lv, Xuekai Zhu, Zhouhan Lin, Zilong Zheng","submitted_at":"2024-12-19T09:43:39Z","abstract_excerpt":"Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic data will fundamentally reshape the web data ecosystem. Future GPT-$\\{n\\}$ models will inevitably be trained on a blend of synthetic and human-produced data. In this paper, we focus on two questions: what is the impact of synthetic data on language model training, and how to synthesize data without model collapse? We first pre-train language models across different proportions of synthetic data, revealing a negative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14689","kind":"arxiv","version":3},"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/2412.14689/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":"2026-07-05T11:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FjWh69JUmfys32j05pjVYfi8UzuJA+dyCBmnW9PqE47vshvVXnMIWhC03e1uShydFUOuAT+/CNkbhbnbujJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:42:31.998244Z"},"content_sha256":"b69efa44f6da1c46f5b70467774184a64e4b6bde781430593601b0dcada0c85c","schema_version":"1.0","event_id":"sha256:b69efa44f6da1c46f5b70467774184a64e4b6bde781430593601b0dcada0c85c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ/bundle.json","state_url":"https://pith.science/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ/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":"2026-08-03T14:42:32Z","links":{"resolver":"https://pith.science/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ","bundle":"https://pith.science/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ/bundle.json","state":"https://pith.science/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VMFX7YHVPVDO7H7XUQUBKXHHKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VMFX7YHVPVDO7H7XUQUBKXHHKJ","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":"e91d91c0d6d8382420e94c820b98f689df9d007060b8f232ba5d9b7bf18913e8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T09:43:39Z","title_canon_sha256":"73ec5819b38d42cfe5fdf4a9e6abd6eda5d2251a93ed6d666bf1dac570984b9a"},"schema_version":"1.0","source":{"id":"2412.14689","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14689","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14689v3","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14689","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"VMFX7YHVPVDO","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"VMFX7YHVPVDO7H7X","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"VMFX7YHV","created_at":"2026-07-05T11:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:b69efa44f6da1c46f5b70467774184a64e4b6bde781430593601b0dcada0c85c","target":"graph","created_at":"2026-07-05T11:10:49Z","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/2412.14689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic data will fundamentally reshape the web data ecosystem. Future GPT-$\\{n\\}$ models will inevitably be trained on a blend of synthetic and human-produced data. In this paper, we focus on two questions: what is the impact of synthetic data on language model training, and how to synthesize data without model collapse? We first pre-train language models across different proportions of synthetic data, revealing a negative ","authors_text":"Bowen Zhou, Daixuan Cheng, Ermo Hua, Hengli Li, Kaiyan Zhang, Ning Ding, Xingtai Lv, Xuekai Zhu, Zhouhan Lin, Zilong Zheng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T09:43:39Z","title":"How to Synthesize Text Data without Model Collapse?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14689","kind":"arxiv","version":3},"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:ef052af507a22c382f3cdd46ba83b108118f141ebd03c4c46e0aad44794ede30","target":"record","created_at":"2026-07-05T11:10:49Z","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":"e91d91c0d6d8382420e94c820b98f689df9d007060b8f232ba5d9b7bf18913e8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T09:43:39Z","title_canon_sha256":"73ec5819b38d42cfe5fdf4a9e6abd6eda5d2251a93ed6d666bf1dac570984b9a"},"schema_version":"1.0","source":{"id":"2412.14689","kind":"arxiv","version":3}},"canonical_sha256":"ab0b7fe0f57d46ef9ff7a428155ce75268787541e126c5bd8bc6742e02b8e062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab0b7fe0f57d46ef9ff7a428155ce75268787541e126c5bd8bc6742e02b8e062","first_computed_at":"2026-07-05T11:10:49.684185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:49.684185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NGV9T8ftijDctcdjz6xrL2QhqgQJJ8unR09urw58c3oKFeMP0N5Md2HPhUP4JeKKMMQktqNQFl5gzYJ/FbG/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:49.684745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14689","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef052af507a22c382f3cdd46ba83b108118f141ebd03c4c46e0aad44794ede30","sha256:b69efa44f6da1c46f5b70467774184a64e4b6bde781430593601b0dcada0c85c"],"state_sha256":"314e746d0effce61f8f831c9930af6a2b64a3e408dd3c84058cd2410ec565902"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BsLMN/MEWJAW/uk9t0pPanY2RDNdm2GL9vMbGoi+oYQVi2b1ngCyYcyh4bDbhtWxpmZleQ4cjosC6GHTyh0GAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:42:32.003755Z","bundle_sha256":"9b3794f6906c5a6e144de6f0036279972b957284bfa7ae00643849af450ca386"}}