{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3RCX7AEZR5N3FXRD2OXXMO3WSL","short_pith_number":"pith:3RCX7AEZ","canonical_record":{"source":{"id":"2305.09235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T07:30:29Z","cross_cats_sorted":[],"title_canon_sha256":"d12d9516925a079482bfb31e907180c3d722883ada8d70f3204666bf0affc58c","abstract_canon_sha256":"5d01a1e7da0d989e98a794d9bc5f15e0fc35f032c8f5404349a9858d92425b87"},"schema_version":"1.0"},"canonical_sha256":"dc457f80998f5bb2de23d3af763b7692e5ab9113498b45c157016c9254fff13c","source":{"kind":"arxiv","id":"2305.09235","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09235","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09235v2","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09235","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"3RCX7AEZR5N3","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"3RCX7AEZR5N3FXRD","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"3RCX7AEZ","created_at":"2026-07-05T06:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3RCX7AEZR5N3FXRD2OXXMO3WSL","target":"record","payload":{"canonical_record":{"source":{"id":"2305.09235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T07:30:29Z","cross_cats_sorted":[],"title_canon_sha256":"d12d9516925a079482bfb31e907180c3d722883ada8d70f3204666bf0affc58c","abstract_canon_sha256":"5d01a1e7da0d989e98a794d9bc5f15e0fc35f032c8f5404349a9858d92425b87"},"schema_version":"1.0"},"canonical_sha256":"dc457f80998f5bb2de23d3af763b7692e5ab9113498b45c157016c9254fff13c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:01.810908Z","signature_b64":"fEtjil6ZFs6d6HEPcurq4Nv81g8V6E6AgXvjMk5g4rdxFuEtTac1tbx86FmzQTyv9ISrlEiu8rZWL5Bchn4hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc457f80998f5bb2de23d3af763b7692e5ab9113498b45c157016c9254fff13c","last_reissued_at":"2026-07-05T06:29:01.810437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:01.810437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.09235","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":"2026-07-05T06:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vWLVSY3cA6SOU1BjJM7b+pPdc/SPkJFfGQbX502sZ1OgZt3xtJB4VBBhB6PEtuPxbA46oyq8JBHhzxnDUnUrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:29:21.444558Z"},"content_sha256":"db3e3ba68de6a081acff2cd5aa39b60b1539d256d49f33f7d5db379635927fd7","schema_version":"1.0","event_id":"sha256:db3e3ba68de6a081acff2cd5aa39b60b1539d256d49f33f7d5db379635927fd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3RCX7AEZR5N3FXRD2OXXMO3WSL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic data, real errors: how (not) to publish and use synthetic data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-05-16T07:30:29Z","abstract_excerpt":"Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs. Unfortunately, synthetic data is usually not perfect, resulting in potential errors in downstream tasks. In this work we explore how the generative process affects the downstream ML task. We show that the naive synthetic data approach -- using synthetic data as if it is real -- leads to downstream models and analyses that do not generalize well to real data. As a first step towards better ML in the synthetic data regime, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09235","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/2305.09235/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":"2026-07-05T06:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CbjVIAmBqVWsqAwGcbVQEOeNzmEUpNtI2drf1P9v0Td+H+us3FSZwGpfEaPGlnRzsfjUrZ2EmOcB503X3W6bDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:29:21.445520Z"},"content_sha256":"2f4eebee3cc3b8df98268c00d855468197cfe9b2a6ab3f38ac139874980e14cf","schema_version":"1.0","event_id":"sha256:2f4eebee3cc3b8df98268c00d855468197cfe9b2a6ab3f38ac139874980e14cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL/bundle.json","state_url":"https://pith.science/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL/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":"2026-08-14T10:29:21Z","links":{"resolver":"https://pith.science/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL","bundle":"https://pith.science/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL/bundle.json","state":"https://pith.science/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RCX7AEZR5N3FXRD2OXXMO3WSL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3RCX7AEZR5N3FXRD2OXXMO3WSL","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":"5d01a1e7da0d989e98a794d9bc5f15e0fc35f032c8f5404349a9858d92425b87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T07:30:29Z","title_canon_sha256":"d12d9516925a079482bfb31e907180c3d722883ada8d70f3204666bf0affc58c"},"schema_version":"1.0","source":{"id":"2305.09235","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09235","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09235v2","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09235","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"3RCX7AEZR5N3","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"3RCX7AEZR5N3FXRD","created_at":"2026-07-05T06:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"3RCX7AEZ","created_at":"2026-07-05T06:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:2f4eebee3cc3b8df98268c00d855468197cfe9b2a6ab3f38ac139874980e14cf","target":"graph","created_at":"2026-07-05T06:29:01Z","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/2305.09235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs. Unfortunately, synthetic data is usually not perfect, resulting in potential errors in downstream tasks. In this work we explore how the generative process affects the downstream ML task. We show that the naive synthetic data approach -- using synthetic data as if it is real -- leads to downstream models and analyses that do not generalize well to real data. As a first step towards better ML in the synthetic data regime, ","authors_text":"Boris van Breugel, Mihaela van der Schaar, Zhaozhi Qian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T07:30:29Z","title":"Synthetic data, real errors: how (not) to publish and use synthetic data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09235","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:db3e3ba68de6a081acff2cd5aa39b60b1539d256d49f33f7d5db379635927fd7","target":"record","created_at":"2026-07-05T06:29:01Z","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":"5d01a1e7da0d989e98a794d9bc5f15e0fc35f032c8f5404349a9858d92425b87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T07:30:29Z","title_canon_sha256":"d12d9516925a079482bfb31e907180c3d722883ada8d70f3204666bf0affc58c"},"schema_version":"1.0","source":{"id":"2305.09235","kind":"arxiv","version":2}},"canonical_sha256":"dc457f80998f5bb2de23d3af763b7692e5ab9113498b45c157016c9254fff13c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc457f80998f5bb2de23d3af763b7692e5ab9113498b45c157016c9254fff13c","first_computed_at":"2026-07-05T06:29:01.810437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:01.810437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fEtjil6ZFs6d6HEPcurq4Nv81g8V6E6AgXvjMk5g4rdxFuEtTac1tbx86FmzQTyv9ISrlEiu8rZWL5Bchn4hAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:01.810908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09235","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db3e3ba68de6a081acff2cd5aa39b60b1539d256d49f33f7d5db379635927fd7","sha256:2f4eebee3cc3b8df98268c00d855468197cfe9b2a6ab3f38ac139874980e14cf"],"state_sha256":"cab5f24265ed50e87b3571199a262679f230985cc43b0d5b71fa750e45f99f29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCHpqf/n3BdsPX71oKA+RECUtAhfAx5U8qhvEoP+GmSB7C3OeT5H4MAlTxDy8EWi1IjJDZW8/QCZKQ3hWGpyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:29:21.457251Z","bundle_sha256":"03bcb89a79de1a965648b7fd333f218bcd6bfe94cb3c354fd28a081e8129d82a"}}