{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IXUUIA2G6AKO7T2P6KQ65VYHGH","short_pith_number":"pith:IXUUIA2G","schema_version":"1.0","canonical_sha256":"45e9440346f014efcf4ff2a1eed70731c3b9ad18c3cf846175e298a61baa0659","source":{"kind":"arxiv","id":"2504.01908","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrey Sidorenko, Mario Scriminaci, Michael Platzer, Paul Tiwald","submitted_at":"2025-04-02T17:10:30Z","abstract_excerpt":"Evaluating the quality of synthetic data remains a key challenge for ensuring privacy and utility in data-driven research. In this work, we present an evaluation framework that quantifies how well synthetic data replicates original distributional properties while ensuring privacy. The proposed approach employs a holdout-based benchmarking strategy that facilitates quantitative assessment through low- and high-dimensional distribution comparisons, embedding-based similarity measures, and nearest-neighbor distance metrics. The framework supports various data types and structures, including seque"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.01908","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T17:10:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73198aff8cb7267b1042e78f54804776cb7017d58f8be5456a9b20a4e8560541","abstract_canon_sha256":"6da897f277d6622985d79cf02882b7b0a44b9a7090ff4b44584f29e068c27a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:31.646701Z","signature_b64":"dTsiheOaEFhtG/Ig7NIv5VvQdZVICF4ke29A0PVmvk9X6GTbmYdbrRn5ACTfWN5jaLTeW/LU21NrM6OcWRkqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e9440346f014efcf4ff2a1eed70731c3b9ad18c3cf846175e298a61baa0659","last_reissued_at":"2026-07-05T10:43:31.646208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:31.646208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrey Sidorenko, Mario Scriminaci, Michael Platzer, Paul Tiwald","submitted_at":"2025-04-02T17:10:30Z","abstract_excerpt":"Evaluating the quality of synthetic data remains a key challenge for ensuring privacy and utility in data-driven research. In this work, we present an evaluation framework that quantifies how well synthetic data replicates original distributional properties while ensuring privacy. The proposed approach employs a holdout-based benchmarking strategy that facilitates quantitative assessment through low- and high-dimensional distribution comparisons, embedding-based similarity measures, and nearest-neighbor distance metrics. The framework supports various data types and structures, including seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01908","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/2504.01908/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.01908","created_at":"2026-07-05T10:43:31.646265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01908v1","created_at":"2026-07-05T10:43:31.646265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01908","created_at":"2026-07-05T10:43:31.646265+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXUUIA2G6AKO","created_at":"2026-07-05T10:43:31.646265+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXUUIA2G6AKO7T2P","created_at":"2026-07-05T10:43:31.646265+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXUUIA2G","created_at":"2026-07-05T10:43:31.646265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08736","citing_title":"Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH","json":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH.json","graph_json":"https://pith.science/api/pith-number/IXUUIA2G6AKO7T2P6KQ65VYHGH/graph.json","events_json":"https://pith.science/api/pith-number/IXUUIA2G6AKO7T2P6KQ65VYHGH/events.json","paper":"https://pith.science/paper/IXUUIA2G"},"agent_actions":{"view_html":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH","download_json":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH.json","view_paper":"https://pith.science/paper/IXUUIA2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01908&json=true","fetch_graph":"https://pith.science/api/pith-number/IXUUIA2G6AKO7T2P6KQ65VYHGH/graph.json","fetch_events":"https://pith.science/api/pith-number/IXUUIA2G6AKO7T2P6KQ65VYHGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH/action/storage_attestation","attest_author":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH/action/author_attestation","sign_citation":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH/action/citation_signature","submit_replication":"https://pith.science/pith/IXUUIA2G6AKO7T2P6KQ65VYHGH/action/replication_record"}},"created_at":"2026-07-05T10:43:31.646265+00:00","updated_at":"2026-07-05T10:43:31.646265+00:00"}