{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G6M3D46K73W6OESNBZ5GEW2PCZ","short_pith_number":"pith:G6M3D46K","canonical_record":{"source":{"id":"2306.15636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-27T17:26:23Z","cross_cats_sorted":[],"title_canon_sha256":"a5b20579fa077b6ce1474a93b6086d39aed47afa5a525a62e3c1dbb8d6b7c5fc","abstract_canon_sha256":"2d6eee36c58fac37d7f483efe914c724a368dfeb0012dac524bcb086fe686fb0"},"schema_version":"1.0"},"canonical_sha256":"3799b1f3cafeede7124d0e7a625b4f166d0eb22bbda50897e37a055e33eddc26","source":{"kind":"arxiv","id":"2306.15636","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15636","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15636v1","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15636","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"G6M3D46K73W6","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"G6M3D46K73W6OESN","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"G6M3D46K","created_at":"2026-07-05T06:25:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G6M3D46K73W6OESNBZ5GEW2PCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.15636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-27T17:26:23Z","cross_cats_sorted":[],"title_canon_sha256":"a5b20579fa077b6ce1474a93b6086d39aed47afa5a525a62e3c1dbb8d6b7c5fc","abstract_canon_sha256":"2d6eee36c58fac37d7f483efe914c724a368dfeb0012dac524bcb086fe686fb0"},"schema_version":"1.0"},"canonical_sha256":"3799b1f3cafeede7124d0e7a625b4f166d0eb22bbda50897e37a055e33eddc26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:35.103683Z","signature_b64":"sc7iNRd8TW79OQs/luGgTzx5wT+NAPb8xCJ1QXJc5fBnOFU6hK9UBZocUXf15WRt2Ub0vV2ulrQvijphx/fxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3799b1f3cafeede7124d0e7a625b4f166d0eb22bbda50897e37a055e33eddc26","last_reissued_at":"2026-07-05T06:25:35.103222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:35.103222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.15636","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lwy8BOsyuD5x8rxwTy5IyAAJp1AaUufyiUWVCcUM8hMguJ5B68ElW+icTXAOpaeM9dshiieuFWvyQszBapK0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:46:47.316820Z"},"content_sha256":"75eb21c02df445e3c8505e62cc1da8b324f2713f0845c88f4ed80a6c4370a7e8","schema_version":"1.0","event_id":"sha256:75eb21c02df445e3c8505e62cc1da8b324f2713f0845c88f4ed80a6c4370a7e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G6M3D46K73W6OESNBZ5GEW2PCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Usefulness of Synthetic Tabular Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dionysis Manousakas, Serg\\\"ul Ayd\\\"ore","submitted_at":"2023-06-27T17:26:23Z","abstract_excerpt":"Despite recent advances in synthetic data generation, the scientific community still lacks a unified consensus on its usefulness. It is commonly believed that synthetic data can be used for both data exchange and boosting machine learning (ML) training. Privacy-preserving synthetic data generation can accelerate data exchange for downstream tasks, but there is not enough evidence to show how or why synthetic data can boost ML training. In this study, we benchmarked ML performance using synthetic tabular data for four use cases: data sharing, data augmentation, class balancing, and data summari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15636","kind":"arxiv","version":1},"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/2306.15636/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":"2026-07-05T06:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCju2ABtS80AzX44RL18UKhl/H/NuqKM9IxDdVZODMEobQ2Qr4HsZMSdqFZbuNM7ajL7f7BrU0ReaaM1I4NuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:46:47.317309Z"},"content_sha256":"902968ebf489588ee759387d7562207cd2d8ab3885bc4a1fcb793fe7771e29b0","schema_version":"1.0","event_id":"sha256:902968ebf489588ee759387d7562207cd2d8ab3885bc4a1fcb793fe7771e29b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6M3D46K73W6OESNBZ5GEW2PCZ/bundle.json","state_url":"https://pith.science/pith/G6M3D46K73W6OESNBZ5GEW2PCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6M3D46K73W6OESNBZ5GEW2PCZ/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":"2026-08-08T11:46:47Z","links":{"resolver":"https://pith.science/pith/G6M3D46K73W6OESNBZ5GEW2PCZ","bundle":"https://pith.science/pith/G6M3D46K73W6OESNBZ5GEW2PCZ/bundle.json","state":"https://pith.science/pith/G6M3D46K73W6OESNBZ5GEW2PCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6M3D46K73W6OESNBZ5GEW2PCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G6M3D46K73W6OESNBZ5GEW2PCZ","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":"2d6eee36c58fac37d7f483efe914c724a368dfeb0012dac524bcb086fe686fb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-27T17:26:23Z","title_canon_sha256":"a5b20579fa077b6ce1474a93b6086d39aed47afa5a525a62e3c1dbb8d6b7c5fc"},"schema_version":"1.0","source":{"id":"2306.15636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15636","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15636v1","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15636","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"G6M3D46K73W6","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"G6M3D46K73W6OESN","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"G6M3D46K","created_at":"2026-07-05T06:25:35Z"}],"graph_snapshots":[{"event_id":"sha256:902968ebf489588ee759387d7562207cd2d8ab3885bc4a1fcb793fe7771e29b0","target":"graph","created_at":"2026-07-05T06:25:35Z","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/2306.15636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in synthetic data generation, the scientific community still lacks a unified consensus on its usefulness. It is commonly believed that synthetic data can be used for both data exchange and boosting machine learning (ML) training. Privacy-preserving synthetic data generation can accelerate data exchange for downstream tasks, but there is not enough evidence to show how or why synthetic data can boost ML training. In this study, we benchmarked ML performance using synthetic tabular data for four use cases: data sharing, data augmentation, class balancing, and data summari","authors_text":"Dionysis Manousakas, Serg\\\"ul Ayd\\\"ore","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-27T17:26:23Z","title":"On the Usefulness of Synthetic Tabular Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15636","kind":"arxiv","version":1},"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":"sha256:75eb21c02df445e3c8505e62cc1da8b324f2713f0845c88f4ed80a6c4370a7e8","target":"record","created_at":"2026-07-05T06:25:35Z","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":"2d6eee36c58fac37d7f483efe914c724a368dfeb0012dac524bcb086fe686fb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-27T17:26:23Z","title_canon_sha256":"a5b20579fa077b6ce1474a93b6086d39aed47afa5a525a62e3c1dbb8d6b7c5fc"},"schema_version":"1.0","source":{"id":"2306.15636","kind":"arxiv","version":1}},"canonical_sha256":"3799b1f3cafeede7124d0e7a625b4f166d0eb22bbda50897e37a055e33eddc26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3799b1f3cafeede7124d0e7a625b4f166d0eb22bbda50897e37a055e33eddc26","first_computed_at":"2026-07-05T06:25:35.103222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:35.103222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sc7iNRd8TW79OQs/luGgTzx5wT+NAPb8xCJ1QXJc5fBnOFU6hK9UBZocUXf15WRt2Ub0vV2ulrQvijphx/fxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:35.103683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75eb21c02df445e3c8505e62cc1da8b324f2713f0845c88f4ed80a6c4370a7e8","sha256:902968ebf489588ee759387d7562207cd2d8ab3885bc4a1fcb793fe7771e29b0"],"state_sha256":"ec9f7ddd7108eb9b57aa01fbc8781a2c657e7e3fb2e57d11b7318e0bf82a1cfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYG9TyThOk2M43pgwuljmKnAgZuZYEIG7+hNWa5Z1TClqGrQdssiu25dOG+ToYpH9g/xoSbDZ8h9JsV4S5yvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:46:47.321683Z","bundle_sha256":"eb5f7a0dce575420da89d53081342761e6aa22aac14f1ece621911d87a085d96"}}