{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OABUZBT74MJLEQ5CJDUZ3ZQUOW","short_pith_number":"pith:OABUZBT7","schema_version":"1.0","canonical_sha256":"70034c867fe312b243a248e99de614758699654055af59f324b45bb1969ce7d8","source":{"kind":"arxiv","id":"2309.06526","version":1},"attestation_state":"computed","paper":{"title":"Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Pin-Yu Chen, Xilong Wang","submitted_at":"2023-09-12T19:08:26Z","abstract_excerpt":"For machine learning with tabular data, Table Transformer (TabTransformer) is a state-of-the-art neural network model, while Differential Privacy (DP) is an essential component to ensure data privacy. In this paper, we explore the benefits of combining these two aspects together in the scenario of transfer learning -- differentially private pre-training and fine-tuning of TabTransformers with a variety of parameter-efficient fine-tuning (PEFT) methods, including Adapter, LoRA, and Prompt Tuning. Our extensive experiments on the ACSIncome dataset show that these PEFT methods outperform traditio"},"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":"2309.06526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T19:08:26Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"386a44e93665bf9a0899ca0f8660192314df1a031f6a205d6f29db287e9c735a","abstract_canon_sha256":"1893a8a8d7d0bc0710ae5236479ef06e767dbb097eb40d5c0b518b9564486673"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:19.011894Z","signature_b64":"m9ZvuQ3g4tkiAjw6BSZYXo4Ci78UeiVCrxYWs2xx93wjUP3pNOc8quMqSLKk1D/CKNIVGbGoba4tWUB04BxEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70034c867fe312b243a248e99de614758699654055af59f324b45bb1969ce7d8","last_reissued_at":"2026-07-05T06:50:19.011411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:19.011411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Pin-Yu Chen, Xilong Wang","submitted_at":"2023-09-12T19:08:26Z","abstract_excerpt":"For machine learning with tabular data, Table Transformer (TabTransformer) is a state-of-the-art neural network model, while Differential Privacy (DP) is an essential component to ensure data privacy. In this paper, we explore the benefits of combining these two aspects together in the scenario of transfer learning -- differentially private pre-training and fine-tuning of TabTransformers with a variety of parameter-efficient fine-tuning (PEFT) methods, including Adapter, LoRA, and Prompt Tuning. Our extensive experiments on the ACSIncome dataset show that these PEFT methods outperform traditio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06526","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/2309.06526/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":"2309.06526","created_at":"2026-07-05T06:50:19.011473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06526v1","created_at":"2026-07-05T06:50:19.011473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06526","created_at":"2026-07-05T06:50:19.011473+00:00"},{"alias_kind":"pith_short_12","alias_value":"OABUZBT74MJL","created_at":"2026-07-05T06:50:19.011473+00:00"},{"alias_kind":"pith_short_16","alias_value":"OABUZBT74MJLEQ5C","created_at":"2026-07-05T06:50:19.011473+00:00"},{"alias_kind":"pith_short_8","alias_value":"OABUZBT7","created_at":"2026-07-05T06:50:19.011473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW","json":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW.json","graph_json":"https://pith.science/api/pith-number/OABUZBT74MJLEQ5CJDUZ3ZQUOW/graph.json","events_json":"https://pith.science/api/pith-number/OABUZBT74MJLEQ5CJDUZ3ZQUOW/events.json","paper":"https://pith.science/paper/OABUZBT7"},"agent_actions":{"view_html":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW","download_json":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW.json","view_paper":"https://pith.science/paper/OABUZBT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06526&json=true","fetch_graph":"https://pith.science/api/pith-number/OABUZBT74MJLEQ5CJDUZ3ZQUOW/graph.json","fetch_events":"https://pith.science/api/pith-number/OABUZBT74MJLEQ5CJDUZ3ZQUOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW/action/storage_attestation","attest_author":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW/action/author_attestation","sign_citation":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW/action/citation_signature","submit_replication":"https://pith.science/pith/OABUZBT74MJLEQ5CJDUZ3ZQUOW/action/replication_record"}},"created_at":"2026-07-05T06:50:19.011473+00:00","updated_at":"2026-07-05T06:50:19.011473+00:00"}