{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OFKQHG6ZUUFO4NIEXK6KYR42ED","short_pith_number":"pith:OFKQHG6Z","schema_version":"1.0","canonical_sha256":"7155039bd9a50aee3504babcac479a20f8c1d20ab08254bbc0470d6f466d9b43","source":{"kind":"arxiv","id":"2408.02927","version":1},"attestation_state":"computed","paper":{"title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Duanyu Feng, Hao Wang, Jimin Huang, Qianqian Xie, Sophia Ananiadou, Yongfu Dai, Yuxin Wang, Zhengyu Chen","submitted_at":"2024-08-06T03:21:13Z","abstract_excerpt":"Data serves as the fundamental foundation for advancing deep learning, particularly tabular data presented in a structured format, which is highly conducive to modeling. However, even in the era of LLM, obtaining tabular data from sensitive domains remains a challenge due to privacy or copyright concerns. Hence, exploring how to effectively use models like LLMs to generate realistic and privacy-preserving synthetic tabular data is urgent. In this paper, we take a step forward to explore LLMs for tabular data synthesis and privacy protection, by introducing a new framework HARMONIC for tabular "},"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":"2408.02927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T03:21:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"title_canon_sha256":"b35ed0ea6233fe6789e68142c05db9d988fc3ea58f1cdc3dd353b092046a3423","abstract_canon_sha256":"4f6f825a94a3a40e61119deeff2249a5a714c82aaa6e841e4d6431e857fa5ef3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:42.427016Z","signature_b64":"jqu7BIUVCEr2qlQjRctIGFRSGGCOlwHKAWP7VS73Tsagu9bEE1IAiRX51jX5iGHiu8Ixcafqwzljq6L6kAW/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7155039bd9a50aee3504babcac479a20f8c1d20ab08254bbc0470d6f466d9b43","last_reissued_at":"2026-07-05T08:52:42.426563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:42.426563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Duanyu Feng, Hao Wang, Jimin Huang, Qianqian Xie, Sophia Ananiadou, Yongfu Dai, Yuxin Wang, Zhengyu Chen","submitted_at":"2024-08-06T03:21:13Z","abstract_excerpt":"Data serves as the fundamental foundation for advancing deep learning, particularly tabular data presented in a structured format, which is highly conducive to modeling. However, even in the era of LLM, obtaining tabular data from sensitive domains remains a challenge due to privacy or copyright concerns. Hence, exploring how to effectively use models like LLMs to generate realistic and privacy-preserving synthetic tabular data is urgent. In this paper, we take a step forward to explore LLMs for tabular data synthesis and privacy protection, by introducing a new framework HARMONIC for tabular "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02927","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/2408.02927/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":"2408.02927","created_at":"2026-07-05T08:52:42.426618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02927v1","created_at":"2026-07-05T08:52:42.426618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02927","created_at":"2026-07-05T08:52:42.426618+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFKQHG6ZUUFO","created_at":"2026-07-05T08:52:42.426618+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFKQHG6ZUUFO4NIE","created_at":"2026-07-05T08:52:42.426618+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFKQHG6Z","created_at":"2026-07-05T08:52:42.426618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.02161","citing_title":"LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09855","citing_title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09855","citing_title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED","json":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED.json","graph_json":"https://pith.science/api/pith-number/OFKQHG6ZUUFO4NIEXK6KYR42ED/graph.json","events_json":"https://pith.science/api/pith-number/OFKQHG6ZUUFO4NIEXK6KYR42ED/events.json","paper":"https://pith.science/paper/OFKQHG6Z"},"agent_actions":{"view_html":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED","download_json":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED.json","view_paper":"https://pith.science/paper/OFKQHG6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02927&json=true","fetch_graph":"https://pith.science/api/pith-number/OFKQHG6ZUUFO4NIEXK6KYR42ED/graph.json","fetch_events":"https://pith.science/api/pith-number/OFKQHG6ZUUFO4NIEXK6KYR42ED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED/action/storage_attestation","attest_author":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED/action/author_attestation","sign_citation":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED/action/citation_signature","submit_replication":"https://pith.science/pith/OFKQHG6ZUUFO4NIEXK6KYR42ED/action/replication_record"}},"created_at":"2026-07-05T08:52:42.426618+00:00","updated_at":"2026-07-05T08:52:42.426618+00:00"}