{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BTZKXUJICJYFUAEYX4ZKLG7PXZ","short_pith_number":"pith:BTZKXUJI","schema_version":"1.0","canonical_sha256":"0cf2abd12812705a0098bf32a59befbe73a6c9ea0e5821d7e44b658d87641f62","source":{"kind":"arxiv","id":"2506.12619","version":1},"attestation_state":"computed","paper":{"title":"Semivalue-based data valuation is arbitrary and gameable","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Ashia C. Wilson, Hannah Diehl","submitted_at":"2025-06-14T20:20:15Z","abstract_excerpt":"The game-theoretic notion of the semivalue offers a popular framework for credit attribution and data valuation in machine learning. Semivalues have been proposed for a variety of high-stakes decisions involving data, such as determining contributor compensation, acquiring data from external sources, or filtering out low-value datapoints. In these applications, semivalues depend on the specification of a utility function that maps subsets of data to a scalar score. While it is broadly agreed that this utility function arises from a composition of a learning algorithm and a performance metric, "},"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":"2506.12619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T20:20:15Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"a281660e8d65cf1e880ab988fda25ab490d9efb88994ce469d4718cc8498bb29","abstract_canon_sha256":"08373d537c69951b4cfaff03da7718603b02240f2ce20a1de71fd516dc8a7337"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:56.410181Z","signature_b64":"eve7OStQgedU0BOjTeMN0eaTiJWWGXmoTTM4HqkiHUT9yWRSjpH4DEFzok8yRp3M2o/SdxrV8pTu1qDkQe7rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cf2abd12812705a0098bf32a59befbe73a6c9ea0e5821d7e44b658d87641f62","last_reissued_at":"2026-07-05T11:21:56.409780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:56.409780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semivalue-based data valuation is arbitrary and gameable","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Ashia C. Wilson, Hannah Diehl","submitted_at":"2025-06-14T20:20:15Z","abstract_excerpt":"The game-theoretic notion of the semivalue offers a popular framework for credit attribution and data valuation in machine learning. Semivalues have been proposed for a variety of high-stakes decisions involving data, such as determining contributor compensation, acquiring data from external sources, or filtering out low-value datapoints. In these applications, semivalues depend on the specification of a utility function that maps subsets of data to a scalar score. While it is broadly agreed that this utility function arises from a composition of a learning algorithm and a performance metric, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12619","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/2506.12619/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":"2506.12619","created_at":"2026-07-05T11:21:56.409833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12619v1","created_at":"2026-07-05T11:21:56.409833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12619","created_at":"2026-07-05T11:21:56.409833+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTZKXUJICJYF","created_at":"2026-07-05T11:21:56.409833+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTZKXUJICJYFUAEY","created_at":"2026-07-05T11:21:56.409833+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTZKXUJI","created_at":"2026-07-05T11:21:56.409833+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/BTZKXUJICJYFUAEYX4ZKLG7PXZ","json":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ.json","graph_json":"https://pith.science/api/pith-number/BTZKXUJICJYFUAEYX4ZKLG7PXZ/graph.json","events_json":"https://pith.science/api/pith-number/BTZKXUJICJYFUAEYX4ZKLG7PXZ/events.json","paper":"https://pith.science/paper/BTZKXUJI"},"agent_actions":{"view_html":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ","download_json":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ.json","view_paper":"https://pith.science/paper/BTZKXUJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12619&json=true","fetch_graph":"https://pith.science/api/pith-number/BTZKXUJICJYFUAEYX4ZKLG7PXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BTZKXUJICJYFUAEYX4ZKLG7PXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ/action/storage_attestation","attest_author":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ/action/author_attestation","sign_citation":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ/action/citation_signature","submit_replication":"https://pith.science/pith/BTZKXUJICJYFUAEYX4ZKLG7PXZ/action/replication_record"}},"created_at":"2026-07-05T11:21:56.409833+00:00","updated_at":"2026-07-05T11:21:56.409833+00:00"}