{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3ZVQSJPD5THUA5RKBAY3HBMQ6C","short_pith_number":"pith:3ZVQSJPD","canonical_record":{"source":{"id":"2506.17847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T22:45:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c7fde1fb4b50a86f9e3069c000e5671db9d096f4895144ecf482bcba4f598d8","abstract_canon_sha256":"adfbd2d7ada4a790efd0a622ae3e1ad600a6ee00c3ec65298a70f0b9aeba73fa"},"schema_version":"1.0"},"canonical_sha256":"de6b0925e3eccf40762a0831b38590f0b1474f514ac9b46d6714897affcf8fba","source":{"kind":"arxiv","id":"2506.17847","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17847","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17847v1","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17847","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"3ZVQSJPD5THU","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"3ZVQSJPD5THUA5RK","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"3ZVQSJPD","created_at":"2026-07-05T11:25:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3ZVQSJPD5THUA5RKBAY3HBMQ6C","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T22:45:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c7fde1fb4b50a86f9e3069c000e5671db9d096f4895144ecf482bcba4f598d8","abstract_canon_sha256":"adfbd2d7ada4a790efd0a622ae3e1ad600a6ee00c3ec65298a70f0b9aeba73fa"},"schema_version":"1.0"},"canonical_sha256":"de6b0925e3eccf40762a0831b38590f0b1474f514ac9b46d6714897affcf8fba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:24.239954Z","signature_b64":"ExUC2o4vn0zoz71oAMqnVFSSYx8Tmuq2uOltmjuP/u2n2zNncnneDeRFnuMXcY2yqb60IOgppS3lZoP1gZGoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6b0925e3eccf40762a0831b38590f0b1474f514ac9b46d6714897affcf8fba","last_reissued_at":"2026-07-05T11:25:24.239513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:24.239513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17847","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":"2026-07-05T11:25:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EtNILJ+xh0HJD+EmWSc0L90a+C+N3lMqLr48plBOIrxVyQkxaa/EC+STLhv9htXKX4qWR9ukaYmZpbJtIRj+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:00:52.994889Z"},"content_sha256":"6863ffbcaa334bcedb83502907564e012ffd4575ff6a12e11a52b6a363c6fc4a","schema_version":"1.0","event_id":"sha256:6863ffbcaa334bcedb83502907564e012ffd4575ff6a12e11a52b6a363c6fc4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3ZVQSJPD5THUA5RKBAY3HBMQ6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cristian Del Gobbo","submitted_at":"2025-06-21T22:45:40Z","abstract_excerpt":"High-quality training data is critical to the performance of machine learning models, particularly Large Language Models (LLMs). However, obtaining real, high-quality data can be challenging, especially for smaller organizations and early-stage startups. Synthetic data generators provide a promising solution by replicating the statistical and structural properties of real data while preserving privacy and scalability. This study evaluates the performance of six tabular synthetic data generators from two widely used open-source libraries: SDV (Gaussian Copula, CTGAN, TVAE) and Synthicity (Bayes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17847","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/2506.17847/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":"2026-07-05T11:25:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T9TI05mpsrsCJl9iKF+0Y1NZxaMksJ4/3FATT7aa1pWKhYKHbm8l3ROBow6xBWOxH+fH6xWaAJUPjnt1e+FKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:00:52.995264Z"},"content_sha256":"c9c5e05a89870b59d567b39af9ec494ea6f7de8d8f902f38b03a2074e15383cc","schema_version":"1.0","event_id":"sha256:c9c5e05a89870b59d567b39af9ec494ea6f7de8d8f902f38b03a2074e15383cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C/bundle.json","state_url":"https://pith.science/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C/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":"2026-08-19T15:00:52Z","links":{"resolver":"https://pith.science/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C","bundle":"https://pith.science/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C/bundle.json","state":"https://pith.science/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZVQSJPD5THUA5RKBAY3HBMQ6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3ZVQSJPD5THUA5RKBAY3HBMQ6C","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":"adfbd2d7ada4a790efd0a622ae3e1ad600a6ee00c3ec65298a70f0b9aeba73fa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T22:45:40Z","title_canon_sha256":"5c7fde1fb4b50a86f9e3069c000e5671db9d096f4895144ecf482bcba4f598d8"},"schema_version":"1.0","source":{"id":"2506.17847","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17847","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17847v1","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17847","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"3ZVQSJPD5THU","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"3ZVQSJPD5THUA5RK","created_at":"2026-07-05T11:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"3ZVQSJPD","created_at":"2026-07-05T11:25:24Z"}],"graph_snapshots":[{"event_id":"sha256:c9c5e05a89870b59d567b39af9ec494ea6f7de8d8f902f38b03a2074e15383cc","target":"graph","created_at":"2026-07-05T11:25:24Z","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/2506.17847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality training data is critical to the performance of machine learning models, particularly Large Language Models (LLMs). However, obtaining real, high-quality data can be challenging, especially for smaller organizations and early-stage startups. Synthetic data generators provide a promising solution by replicating the statistical and structural properties of real data while preserving privacy and scalability. This study evaluates the performance of six tabular synthetic data generators from two widely used open-source libraries: SDV (Gaussian Copula, CTGAN, TVAE) and Synthicity (Bayes","authors_text":"Cristian Del Gobbo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T22:45:40Z","title":"A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17847","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":"sha256:6863ffbcaa334bcedb83502907564e012ffd4575ff6a12e11a52b6a363c6fc4a","target":"record","created_at":"2026-07-05T11:25:24Z","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":"adfbd2d7ada4a790efd0a622ae3e1ad600a6ee00c3ec65298a70f0b9aeba73fa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T22:45:40Z","title_canon_sha256":"5c7fde1fb4b50a86f9e3069c000e5671db9d096f4895144ecf482bcba4f598d8"},"schema_version":"1.0","source":{"id":"2506.17847","kind":"arxiv","version":1}},"canonical_sha256":"de6b0925e3eccf40762a0831b38590f0b1474f514ac9b46d6714897affcf8fba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de6b0925e3eccf40762a0831b38590f0b1474f514ac9b46d6714897affcf8fba","first_computed_at":"2026-07-05T11:25:24.239513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:24.239513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ExUC2o4vn0zoz71oAMqnVFSSYx8Tmuq2uOltmjuP/u2n2zNncnneDeRFnuMXcY2yqb60IOgppS3lZoP1gZGoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:24.239954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17847","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6863ffbcaa334bcedb83502907564e012ffd4575ff6a12e11a52b6a363c6fc4a","sha256:c9c5e05a89870b59d567b39af9ec494ea6f7de8d8f902f38b03a2074e15383cc"],"state_sha256":"f4a3a2b1fd1b1a152bd71f3b952781d9ee909a18b5c5fc558a8c6fe6636038f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCKxUzu++L+mGs6PTbhlQrJEmvt3s6ZOJrfaeAesxpa4/4+vfGMivDunCZw9VSHaV9NBR/ygVn7xgCu1xCjGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:00:52.997803Z","bundle_sha256":"bbef63bfcd84af4f3e6d041accaa32fe618722a6fabb20294e8dca3881b92909"}}