{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C7EAEXQQDGXSLQO4XUEBJZKX2K","short_pith_number":"pith:C7EAEXQQ","schema_version":"1.0","canonical_sha256":"17c8025e1019af25c1dcbd0814e557d2b49cf794abcb9489238d19db5aeb1e90","source":{"kind":"arxiv","id":"2509.00693","version":1},"attestation_state":"computed","paper":{"title":"DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anjali Kaushik, Arun Vignesh Malarkkan, Haoyue Bai, Yanjie Fu","submitted_at":"2025-08-31T04:18:42Z","abstract_excerpt":"In real-world applications, domain data often contains identifiable or sensitive attributes, is subject to strict regulations (e.g., HIPAA, GDPR), and requires explicit data feature engineering for interpretability and transparency. Existing feature engineering primarily focuses on advancing downstream task performance, often risking privacy leakage. We generalize this learning task under such new requirements as Privacy-Preserving Data Reprogramming (PPDR): given a dataset, transforming features to maximize target attribute prediction accuracy while minimizing sensitive attribute prediction a"},"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":"2509.00693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-31T04:18:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"581c112d16c18c98cab950129c9be29b017b8f5279fb8751e845378dacd8e292","abstract_canon_sha256":"56866f76404fb840ed5b835e6446a1fb7e97acf4dc68957109462e5dbfe464dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:21.266825Z","signature_b64":"3xUc86xyq5qyBlabRAwK9P3rEnYZ3hJRey2NkpXUDN4p1ilxPtLz4WkKDrPfbk6b7Fj8KZPhrfnxI4+2/oTpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17c8025e1019af25c1dcbd0814e557d2b49cf794abcb9489238d19db5aeb1e90","last_reissued_at":"2026-07-05T12:02:21.266354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:21.266354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anjali Kaushik, Arun Vignesh Malarkkan, Haoyue Bai, Yanjie Fu","submitted_at":"2025-08-31T04:18:42Z","abstract_excerpt":"In real-world applications, domain data often contains identifiable or sensitive attributes, is subject to strict regulations (e.g., HIPAA, GDPR), and requires explicit data feature engineering for interpretability and transparency. Existing feature engineering primarily focuses on advancing downstream task performance, often risking privacy leakage. We generalize this learning task under such new requirements as Privacy-Preserving Data Reprogramming (PPDR): given a dataset, transforming features to maximize target attribute prediction accuracy while minimizing sensitive attribute prediction a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00693","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/2509.00693/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":"2509.00693","created_at":"2026-07-05T12:02:21.266409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00693v1","created_at":"2026-07-05T12:02:21.266409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00693","created_at":"2026-07-05T12:02:21.266409+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7EAEXQQDGXS","created_at":"2026-07-05T12:02:21.266409+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7EAEXQQDGXSLQO4","created_at":"2026-07-05T12:02:21.266409+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7EAEXQQ","created_at":"2026-07-05T12:02:21.266409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07585","citing_title":"Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach","ref_index":152,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K","json":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K.json","graph_json":"https://pith.science/api/pith-number/C7EAEXQQDGXSLQO4XUEBJZKX2K/graph.json","events_json":"https://pith.science/api/pith-number/C7EAEXQQDGXSLQO4XUEBJZKX2K/events.json","paper":"https://pith.science/paper/C7EAEXQQ"},"agent_actions":{"view_html":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K","download_json":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K.json","view_paper":"https://pith.science/paper/C7EAEXQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00693&json=true","fetch_graph":"https://pith.science/api/pith-number/C7EAEXQQDGXSLQO4XUEBJZKX2K/graph.json","fetch_events":"https://pith.science/api/pith-number/C7EAEXQQDGXSLQO4XUEBJZKX2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K/action/storage_attestation","attest_author":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K/action/author_attestation","sign_citation":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K/action/citation_signature","submit_replication":"https://pith.science/pith/C7EAEXQQDGXSLQO4XUEBJZKX2K/action/replication_record"}},"created_at":"2026-07-05T12:02:21.266409+00:00","updated_at":"2026-07-05T12:02:21.266409+00:00"}