{"as_of":"2026-08-08T23:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:238fdbff8ef39b078a6145c36f58528fd5819cccf1263e6923321535fcc43edc","coverage":[{"denominator":4,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:47:36.596072Z","state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.13818/citation-record","integrity":"/paper/2506.13818/integrity","json":"/paper/2506.13818/citation-record.json","paper":"/paper/2506.13818"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.04325","last_updated":"2024-06-04T22:09:46Z","snapshot_observed_at":"2026-08-07T22:09:30.469726Z","submitted_at":"2022-10-26T00:28:40Z","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.04325","snapshot_observed_at":"2026-08-07T00:47:36.431460Z","title":"Is Synthetic Data the Future of AI?,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13818","last_updated":"2025-06-15T02:10:02Z","snapshot_observed_at":"2026-08-07T20:29:20.398475Z","submitted_at":"2025-06-15T02:10:02Z","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:36.431460Z"},"links":{"cited_paper":"/paper/2211.04325","citing_paper":"/paper/2506.13818"},"observation_digest":"sha256:6ea3b36d0678c2c94a6e41eabcb4e1b265603578b8eec46ce5fac6e58a52fba0","observation_id":"509c0d6b-3565-443d-ae07-842750376b53","resolution":{"observed_at":"2026-08-07T00:47:36.431460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.02245","last_updated":"2021-01-31T15:52:08Z","snapshot_observed_at":"2026-07-06T09:02:13.895931Z","submitted_at":"2020-03-04T18:35:19Z","title":"Data Augmentation using Pre-trained Transformer Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.02245","snapshot_observed_at":"2026-08-07T00:47:36.509825Z","title":"Variational Autoencoders: How They Work and Why They Matter,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13818","last_updated":"2025-06-15T02:10:02Z","snapshot_observed_at":"2026-08-07T20:29:20.398475Z","submitted_at":"2025-06-15T02:10:02Z","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:36.509825Z"},"links":{"cited_paper":"/paper/2003.02245","citing_paper":"/paper/2506.13818"},"observation_digest":"sha256:435e4a594d6855fdcd61067b40e41acd0f0c023756186ddc30b5891943a1745c","observation_id":"cce13c21-8654-489a-9be0-7db2f5efa282","resolution":{"observed_at":"2026-08-07T00:47:36.509825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.03601","last_updated":"2025-07-19T17:39:17Z","snapshot_observed_at":"2026-08-07T20:27:54.118684Z","submitted_at":"2025-04-04T17:13:57Z","title":"APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.03601","snapshot_observed_at":"2026-08-07T00:47:36.545742Z","title":"APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13818","last_updated":"2025-06-15T02:10:02Z","snapshot_observed_at":"2026-08-07T20:29:20.398475Z","submitted_at":"2025-06-15T02:10:02Z","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:36.545742Z"},"links":{"cited_paper":"/paper/2504.03601","citing_paper":"/paper/2506.13818"},"observation_digest":"sha256:958f9578e7d20a9af63495da5787792d177e094025c8b96e2af40e2b1f5e18de","observation_id":"263efd0e-4ebb-4715-a884-1a9dde7e642c","resolution":{"observed_at":"2026-08-07T00:47:36.545742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11039","last_updated":"2024-05-10T11:48:33Z","snapshot_observed_at":"2026-07-06T16:49:25.400974Z","submitted_at":"2023-11-18T11:15:08Z","title":"Synthetic Data Generation for Bridging Sim2Real Gap in a Production Environment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11039","snapshot_observed_at":"2026-08-07T00:47:36.596072Z","title":"Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13818","last_updated":"2025-06-15T02:10:02Z","snapshot_observed_at":"2026-08-07T20:29:20.398475Z","submitted_at":"2025-06-15T02:10:02Z","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:36.596072Z"},"links":{"cited_paper":"/paper/2311.11039","citing_paper":"/paper/2506.13818"},"observation_digest":"sha256:afef3cc7468465705d552b1a643a1660d90b3b4d726ffda16ab7ba94ac4c3e60","observation_id":"69643c6f-ba57-4e96-9b81-f8d2bae2a878","resolution":{"observed_at":"2026-08-07T00:47:36.596072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.13818","last_updated":"2025-06-15T02:10:02Z","latest_version":1,"primary_category":"cs.CY","snapshot_observed_at":"2026-08-07T20:29:20.398475Z","submitted_at":"2025-06-15T02:10:02Z","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":4},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2506.13818."}