{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KKDCB6UBDCDTYDGUEGOMEZT23A","short_pith_number":"pith:KKDCB6UB","schema_version":"1.0","canonical_sha256":"528620fa8118873c0cd4219cc2667ad8362730c8fa06850a8d8f6d1f19a5b87e","source":{"kind":"arxiv","id":"1908.08619","version":4},"attestation_state":"computed","paper":{"title":"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Boxin Wang, Ce Zhang, Costas J. Spanos, David Dao, Dawn Song, Frances Ann Hubis, Nezihe Merve Gurel, Ruoxi Jia","submitted_at":"2019-08-22T23:09:27Z","abstract_excerpt":"Given a data set $\\mathcal{D}$ containing millions of data points and a data consumer who is willing to pay for \\$$X$ to train a machine learning (ML) model over $\\mathcal{D}$, how should we distribute this \\$$X$ to each data point to reflect its \"value\"? In this paper, we define the \"relative value of data\" via the Shapley value, as it uniquely possesses properties with appealing real-world interpretations, such as fairness, rationality and decentralizability. For general, bounded utility functions, the Shapley value is known to be challenging to compute: to get Shapley values for all $N$ dat"},"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":"1908.08619","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T23:09:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"63e5035ec9c145f698cc31c6f123d5bc51e8110afa3f51084693c2bb29f77141","abstract_canon_sha256":"1e6497bc32d27c6fe788143d6d3f9ac0e9711bd3b9f758e3fc11e96ebe373114"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:03.629435Z","signature_b64":"On0fN5cyahRuHj5Gpel+X0tCpLU1Nso+8KuXry/uC4T7PnhvDwNVwlvJABSiWbEe8tv/i8HpcQUNa31rkXkvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"528620fa8118873c0cd4219cc2667ad8362730c8fa06850a8d8f6d1f19a5b87e","last_reissued_at":"2026-07-05T00:51:03.629036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:03.629036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Boxin Wang, Ce Zhang, Costas J. Spanos, David Dao, Dawn Song, Frances Ann Hubis, Nezihe Merve Gurel, Ruoxi Jia","submitted_at":"2019-08-22T23:09:27Z","abstract_excerpt":"Given a data set $\\mathcal{D}$ containing millions of data points and a data consumer who is willing to pay for \\$$X$ to train a machine learning (ML) model over $\\mathcal{D}$, how should we distribute this \\$$X$ to each data point to reflect its \"value\"? In this paper, we define the \"relative value of data\" via the Shapley value, as it uniquely possesses properties with appealing real-world interpretations, such as fairness, rationality and decentralizability. For general, bounded utility functions, the Shapley value is known to be challenging to compute: to get Shapley values for all $N$ dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08619","kind":"arxiv","version":4},"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/1908.08619/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":"1908.08619","created_at":"2026-07-05T00:51:03.629093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08619v4","created_at":"2026-07-05T00:51:03.629093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08619","created_at":"2026-07-05T00:51:03.629093+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKDCB6UBDCDT","created_at":"2026-07-05T00:51:03.629093+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKDCB6UBDCDTYDGU","created_at":"2026-07-05T00:51:03.629093+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKDCB6UB","created_at":"2026-07-05T00:51:03.629093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18729","citing_title":"TimeLAVA: Learning-Agnostic Valuation for Time Series Data","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12615","citing_title":"Towards Provably Fair Machine Learning: Bayesian Approaches For Consistent and Transparent Predictions","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18729","citing_title":"TimeLAVA: Learning-Agnostic Valuation for Time Series Data","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20620","citing_title":"Dynamic Shapley Computation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08821","citing_title":"Buying Data of Unknown Quality: Fisher Information Procurement Auctions","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A","json":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A.json","graph_json":"https://pith.science/api/pith-number/KKDCB6UBDCDTYDGUEGOMEZT23A/graph.json","events_json":"https://pith.science/api/pith-number/KKDCB6UBDCDTYDGUEGOMEZT23A/events.json","paper":"https://pith.science/paper/KKDCB6UB"},"agent_actions":{"view_html":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A","download_json":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A.json","view_paper":"https://pith.science/paper/KKDCB6UB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08619&json=true","fetch_graph":"https://pith.science/api/pith-number/KKDCB6UBDCDTYDGUEGOMEZT23A/graph.json","fetch_events":"https://pith.science/api/pith-number/KKDCB6UBDCDTYDGUEGOMEZT23A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A/action/storage_attestation","attest_author":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A/action/author_attestation","sign_citation":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A/action/citation_signature","submit_replication":"https://pith.science/pith/KKDCB6UBDCDTYDGUEGOMEZT23A/action/replication_record"}},"created_at":"2026-07-05T00:51:03.629093+00:00","updated_at":"2026-07-05T00:51:03.629093+00:00"}