{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OIUT7AKXRBS7CQLIH3A5VJBAKG","short_pith_number":"pith:OIUT7AKX","schema_version":"1.0","canonical_sha256":"72293f81578865f141683ec1daa4205180ba5ca3bbe3aaf2e435000f9dc4f13c","source":{"kind":"arxiv","id":"2304.04258","version":2},"attestation_state":"computed","paper":{"title":"A Note on \"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms\"","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiachen T. Wang, Ruoxi Jia","submitted_at":"2023-04-09T15:31:53Z","abstract_excerpt":"Data valuation is a growing research field that studies the influence of individual data points for machine learning (ML) models. Data Shapley, inspired by cooperative game theory and economics, is an effective method for data valuation. However, it is well-known that the Shapley value (SV) can be computationally expensive. Fortunately, Jia et al. (2019) showed that for K-Nearest Neighbors (KNN) models, the computation of Data Shapley is surprisingly simple and efficient.\n  In this note, we revisit the work of Jia et al. (2019) and propose a more natural and interpretable utility function that"},"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":"2304.04258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2023-04-09T15:31:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d513d0988da4bcfb649ab5de659157b3e26b8606a5f6a9263a3485be9bf1bb4","abstract_canon_sha256":"8f370625d38f08c9b65a17b2b0cd4131f4819cb8e3215e2ec1ef3cc8a791d1f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:39.983486Z","signature_b64":"df+hdY5lkh66Z5TO0IZ7gl0t6G3oAdl6YlRzq9ou30ooM7/VkRqy0yy07jnKUC+45CEmUaNmGAh2asXffHMICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72293f81578865f141683ec1daa4205180ba5ca3bbe3aaf2e435000f9dc4f13c","last_reissued_at":"2026-07-05T07:16:39.983014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:39.983014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Note on \"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms\"","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiachen T. Wang, Ruoxi Jia","submitted_at":"2023-04-09T15:31:53Z","abstract_excerpt":"Data valuation is a growing research field that studies the influence of individual data points for machine learning (ML) models. Data Shapley, inspired by cooperative game theory and economics, is an effective method for data valuation. However, it is well-known that the Shapley value (SV) can be computationally expensive. Fortunately, Jia et al. (2019) showed that for K-Nearest Neighbors (KNN) models, the computation of Data Shapley is surprisingly simple and efficient.\n  In this note, we revisit the work of Jia et al. (2019) and propose a more natural and interpretable utility function that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04258","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/2304.04258/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":"2304.04258","created_at":"2026-07-05T07:16:39.983072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04258v2","created_at":"2026-07-05T07:16:39.983072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04258","created_at":"2026-07-05T07:16:39.983072+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIUT7AKXRBS7","created_at":"2026-07-05T07:16:39.983072+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIUT7AKXRBS7CQLI","created_at":"2026-07-05T07:16:39.983072+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIUT7AKX","created_at":"2026-07-05T07:16:39.983072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21033","citing_title":"Efficient Banzhaf-Based Data Valuation for $k$-Nearest Neighbors Classification","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG","json":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG.json","graph_json":"https://pith.science/api/pith-number/OIUT7AKXRBS7CQLIH3A5VJBAKG/graph.json","events_json":"https://pith.science/api/pith-number/OIUT7AKXRBS7CQLIH3A5VJBAKG/events.json","paper":"https://pith.science/paper/OIUT7AKX"},"agent_actions":{"view_html":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG","download_json":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG.json","view_paper":"https://pith.science/paper/OIUT7AKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04258&json=true","fetch_graph":"https://pith.science/api/pith-number/OIUT7AKXRBS7CQLIH3A5VJBAKG/graph.json","fetch_events":"https://pith.science/api/pith-number/OIUT7AKXRBS7CQLIH3A5VJBAKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG/action/storage_attestation","attest_author":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG/action/author_attestation","sign_citation":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG/action/citation_signature","submit_replication":"https://pith.science/pith/OIUT7AKXRBS7CQLIH3A5VJBAKG/action/replication_record"}},"created_at":"2026-07-05T07:16:39.983072+00:00","updated_at":"2026-07-05T07:16:39.983072+00:00"}