{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GOPJNNP5THQRRY2SZ4ZAK3GPEP","short_pith_number":"pith:GOPJNNP5","schema_version":"1.0","canonical_sha256":"339e96b5fd99e118e352cf32056ccf23e9be2424c15002bdbe102f1c489277a7","source":{"kind":"arxiv","id":"2502.12794","version":1},"attestation_state":"computed","paper":{"title":"RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Changjiang Li, Fenglong Ma, Tanqiu Jiang, Ting Wang","submitted_at":"2025-02-18T11:56:51Z","abstract_excerpt":"Differentially private diffusion models (DPDMs) harness the remarkable generative capabilities of diffusion models while enforcing differential privacy (DP) for sensitive data. However, existing DPDM training approaches often suffer from significant utility loss, large memory footprint, and expensive inference cost, impeding their practical uses. To overcome such limitations, we present RAPID: Retrieval Augmented PrIvate Diffusion model, a novel approach that integrates retrieval augmented generation (RAG) into DPDM training. Specifically, RAPID leverages available public data to build a knowl"},"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":"2502.12794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-18T11:56:51Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"5436a457ab009e6581f3460a943e1e4c8bfb1d3412a6b70c19ed155697c40756","abstract_canon_sha256":"799d0c73c828cf484737bd3c5adaa3c622995c5ab83f9f3090b0f16006c06125"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:24.287356Z","signature_b64":"X79hn0V1MdVhZTTSpoVmvIlcLllb6Th5x39PPwBfrR8RcC3uGAKODDKO5t3Uhq5D1gIQFv8qJnllGlB44Q2dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"339e96b5fd99e118e352cf32056ccf23e9be2424c15002bdbe102f1c489277a7","last_reissued_at":"2026-07-05T10:16:24.286922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:24.286922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Changjiang Li, Fenglong Ma, Tanqiu Jiang, Ting Wang","submitted_at":"2025-02-18T11:56:51Z","abstract_excerpt":"Differentially private diffusion models (DPDMs) harness the remarkable generative capabilities of diffusion models while enforcing differential privacy (DP) for sensitive data. However, existing DPDM training approaches often suffer from significant utility loss, large memory footprint, and expensive inference cost, impeding their practical uses. To overcome such limitations, we present RAPID: Retrieval Augmented PrIvate Diffusion model, a novel approach that integrates retrieval augmented generation (RAG) into DPDM training. Specifically, RAPID leverages available public data to build a knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12794","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/2502.12794/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":"2502.12794","created_at":"2026-07-05T10:16:24.286974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12794v1","created_at":"2026-07-05T10:16:24.286974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12794","created_at":"2026-07-05T10:16:24.286974+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOPJNNP5THQR","created_at":"2026-07-05T10:16:24.286974+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOPJNNP5THQRRY2S","created_at":"2026-07-05T10:16:24.286974+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOPJNNP5","created_at":"2026-07-05T10:16:24.286974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24808","citing_title":"RealDrive: Retrieval-Augmented Driving with Diffusion Models","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP","json":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP.json","graph_json":"https://pith.science/api/pith-number/GOPJNNP5THQRRY2SZ4ZAK3GPEP/graph.json","events_json":"https://pith.science/api/pith-number/GOPJNNP5THQRRY2SZ4ZAK3GPEP/events.json","paper":"https://pith.science/paper/GOPJNNP5"},"agent_actions":{"view_html":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP","download_json":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP.json","view_paper":"https://pith.science/paper/GOPJNNP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12794&json=true","fetch_graph":"https://pith.science/api/pith-number/GOPJNNP5THQRRY2SZ4ZAK3GPEP/graph.json","fetch_events":"https://pith.science/api/pith-number/GOPJNNP5THQRRY2SZ4ZAK3GPEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP/action/storage_attestation","attest_author":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP/action/author_attestation","sign_citation":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP/action/citation_signature","submit_replication":"https://pith.science/pith/GOPJNNP5THQRRY2SZ4ZAK3GPEP/action/replication_record"}},"created_at":"2026-07-05T10:16:24.286974+00:00","updated_at":"2026-07-05T10:16:24.286974+00:00"}