{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VRV45DIVXH3ITCUBLFHF5PDZON","short_pith_number":"pith:VRV45DIV","schema_version":"1.0","canonical_sha256":"ac6bce8d15b9f6898a81594e5ebc79735a53914bc551cdd4e23c83e79aab8da5","source":{"kind":"arxiv","id":"2107.06336","version":2},"attestation_state":"computed","paper":{"title":"Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruoxi Jia, Tianhao Wang, Yu Yang","submitted_at":"2021-07-13T18:56:04Z","abstract_excerpt":"The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems. Both methods have recently been proposed as a principled solution for data valuation tasks, i.e., quantifying the contribution of individual datum in machine learning. However, both SV and LC suffer computational challenges due to the need for retraining models on combinatorially many data subsets. In this work, we propose to boost the efficiency in computing Shapley value or Least core by learning to estimate the performance of a learning algorithm on unseen data combina"},"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":"2107.06336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T18:56:04Z","cross_cats_sorted":[],"title_canon_sha256":"f7efe0f0e6f11419b042b92ffd657e7677691d272ed6764b28017d13504bcfc3","abstract_canon_sha256":"7e962622d20c62fadc330dc461b16e1611fe37d2bdf3ec1241e528609a42cf33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:27.975365Z","signature_b64":"ASt4F3jyWzMlZJ9bSIAfziFZ5ulSAEvAB9fAaVnerKKdjTD3SOpXNH8SiCzLMCrhBQMAPs5SudaC98e78iN8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac6bce8d15b9f6898a81594e5ebc79735a53914bc551cdd4e23c83e79aab8da5","last_reissued_at":"2026-07-05T04:12:27.974888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:27.974888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruoxi Jia, Tianhao Wang, Yu Yang","submitted_at":"2021-07-13T18:56:04Z","abstract_excerpt":"The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems. Both methods have recently been proposed as a principled solution for data valuation tasks, i.e., quantifying the contribution of individual datum in machine learning. However, both SV and LC suffer computational challenges due to the need for retraining models on combinatorially many data subsets. In this work, we propose to boost the efficiency in computing Shapley value or Least core by learning to estimate the performance of a learning algorithm on unseen data combina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06336","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/2107.06336/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":"2107.06336","created_at":"2026-07-05T04:12:27.974945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.06336v2","created_at":"2026-07-05T04:12:27.974945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06336","created_at":"2026-07-05T04:12:27.974945+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRV45DIVXH3I","created_at":"2026-07-05T04:12:27.974945+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRV45DIVXH3ITCUB","created_at":"2026-07-05T04:12:27.974945+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRV45DIV","created_at":"2026-07-05T04:12:27.974945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON","json":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON.json","graph_json":"https://pith.science/api/pith-number/VRV45DIVXH3ITCUBLFHF5PDZON/graph.json","events_json":"https://pith.science/api/pith-number/VRV45DIVXH3ITCUBLFHF5PDZON/events.json","paper":"https://pith.science/paper/VRV45DIV"},"agent_actions":{"view_html":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON","download_json":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON.json","view_paper":"https://pith.science/paper/VRV45DIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.06336&json=true","fetch_graph":"https://pith.science/api/pith-number/VRV45DIVXH3ITCUBLFHF5PDZON/graph.json","fetch_events":"https://pith.science/api/pith-number/VRV45DIVXH3ITCUBLFHF5PDZON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON/action/storage_attestation","attest_author":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON/action/author_attestation","sign_citation":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON/action/citation_signature","submit_replication":"https://pith.science/pith/VRV45DIVXH3ITCUBLFHF5PDZON/action/replication_record"}},"created_at":"2026-07-05T04:12:27.974945+00:00","updated_at":"2026-07-05T04:12:27.974945+00:00"}