{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NPCD2FKXIAPAHOYHW4TUXFQCRB","short_pith_number":"pith:NPCD2FKX","schema_version":"1.0","canonical_sha256":"6bc43d1557401e03bb07b7274b9602887da4cfa8ed2e864433a6b7581d0a7020","source":{"kind":"arxiv","id":"2308.15709","version":2},"attestation_state":"computed","paper":{"title":"Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiachen T. Wang, Prateek Mittal, Ruoxi Jia, Yuqing Zhu, Yu-Xiang Wang","submitted_at":"2023-08-30T02:12:00Z","abstract_excerpt":"Data valuation aims to quantify the usefulness of individual data sources in training machine learning (ML) models, and is a critical aspect of data-centric ML research. However, data valuation faces significant yet frequently overlooked privacy challenges despite its importance. This paper studies these challenges with a focus on KNN-Shapley, one of the most practical data valuation methods nowadays. We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical difficulties in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome "},"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":"2308.15709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-30T02:12:00Z","cross_cats_sorted":["cs.CR","cs.GT","stat.ML"],"title_canon_sha256":"dcd1b1cea4519f3095afdd2d8f2c40a0fa8c5eeed8528e3ce27e5bd1144024cc","abstract_canon_sha256":"99bc70559d3232910f9c0cef6840920d1521b4b7f9c15acc2b5152e201c12c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:45.794509Z","signature_b64":"b1cXInNiZA/A1NeBrFeuUeaLJ8fVwaZSkSc2UJuFpD5A6HWDVq0xanhCzcV+HxAHe4Y9nwHUxRIAx2C2hFDyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc43d1557401e03bb07b7274b9602887da4cfa8ed2e864433a6b7581d0a7020","last_reissued_at":"2026-07-05T07:16:45.793991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:45.793991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiachen T. Wang, Prateek Mittal, Ruoxi Jia, Yuqing Zhu, Yu-Xiang Wang","submitted_at":"2023-08-30T02:12:00Z","abstract_excerpt":"Data valuation aims to quantify the usefulness of individual data sources in training machine learning (ML) models, and is a critical aspect of data-centric ML research. However, data valuation faces significant yet frequently overlooked privacy challenges despite its importance. This paper studies these challenges with a focus on KNN-Shapley, one of the most practical data valuation methods nowadays. We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical difficulties in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15709","kind":"arxiv","version":2},"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/2308.15709/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":"2308.15709","created_at":"2026-07-05T07:16:45.794058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15709v2","created_at":"2026-07-05T07:16:45.794058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15709","created_at":"2026-07-05T07:16:45.794058+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPCD2FKXIAPA","created_at":"2026-07-05T07:16:45.794058+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPCD2FKXIAPAHOYH","created_at":"2026-07-05T07:16:45.794058+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPCD2FKX","created_at":"2026-07-05T07:16:45.794058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10684","citing_title":"Is Data Shapley Not Better than Random in Data Selection? Ask NASH","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10684","citing_title":"Is Data Shapley Not Better than Random in Data Selection? Ask NASH","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB","json":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB.json","graph_json":"https://pith.science/api/pith-number/NPCD2FKXIAPAHOYHW4TUXFQCRB/graph.json","events_json":"https://pith.science/api/pith-number/NPCD2FKXIAPAHOYHW4TUXFQCRB/events.json","paper":"https://pith.science/paper/NPCD2FKX"},"agent_actions":{"view_html":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB","download_json":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB.json","view_paper":"https://pith.science/paper/NPCD2FKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15709&json=true","fetch_graph":"https://pith.science/api/pith-number/NPCD2FKXIAPAHOYHW4TUXFQCRB/graph.json","fetch_events":"https://pith.science/api/pith-number/NPCD2FKXIAPAHOYHW4TUXFQCRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB/action/storage_attestation","attest_author":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB/action/author_attestation","sign_citation":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB/action/citation_signature","submit_replication":"https://pith.science/pith/NPCD2FKXIAPAHOYHW4TUXFQCRB/action/replication_record"}},"created_at":"2026-07-05T07:16:45.794058+00:00","updated_at":"2026-07-05T07:16:45.794058+00:00"}