{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YV3K7IBLQRWXMR5OVF3GHA6S34","short_pith_number":"pith:YV3K7IBL","schema_version":"1.0","canonical_sha256":"c576afa02b846d7647aea9766383d2df2cb22462f9838a7474ddf0591506469c","source":{"kind":"arxiv","id":"2506.23349","version":2},"attestation_state":"computed","paper":{"title":"A case for data valuation transparency via DValCards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Julienne LaChance, Keziah Naggita","submitted_at":"2025-06-29T17:53:00Z","abstract_excerpt":"Following the rise in popularity of data-centric machine learning (ML), various data valuation methods have been proposed to quantify the contribution of each datapoint to desired ML model performance metrics (e.g., accuracy). Beyond the technical applications of data valuation methods (e.g., data cleaning, data acquisition, etc.), it has been suggested that within the context of data markets, data buyers might utilize such methods to fairly compensate data owners. Here we demonstrate that data valuation metrics are inherently biased and unstable under simple algorithmic design choices, result"},"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":"2506.23349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-29T17:53:00Z","cross_cats_sorted":[],"title_canon_sha256":"bb456e7b86fb9008e28acf00377e2286abe9d442a88f699d30e51460a5427922","abstract_canon_sha256":"0be15d5dd81c1fca20e3727e9348aeb815867275cab4525a72dc1bb614ff8512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:36.976988Z","signature_b64":"5L3Eh53n2WTvW+xmJdDbe69+PKGmIQKkEiNdLsswxi8Mv2+iG9MkBu5o8rO1KKQvEF/O5A5AuWTCkyGf8mFyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c576afa02b846d7647aea9766383d2df2cb22462f9838a7474ddf0591506469c","last_reissued_at":"2026-07-05T11:45:36.976498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:36.976498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A case for data valuation transparency via DValCards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Julienne LaChance, Keziah Naggita","submitted_at":"2025-06-29T17:53:00Z","abstract_excerpt":"Following the rise in popularity of data-centric machine learning (ML), various data valuation methods have been proposed to quantify the contribution of each datapoint to desired ML model performance metrics (e.g., accuracy). Beyond the technical applications of data valuation methods (e.g., data cleaning, data acquisition, etc.), it has been suggested that within the context of data markets, data buyers might utilize such methods to fairly compensate data owners. Here we demonstrate that data valuation metrics are inherently biased and unstable under simple algorithmic design choices, result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23349","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/2506.23349/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":"2506.23349","created_at":"2026-07-05T11:45:36.976557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23349v2","created_at":"2026-07-05T11:45:36.976557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23349","created_at":"2026-07-05T11:45:36.976557+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV3K7IBLQRWX","created_at":"2026-07-05T11:45:36.976557+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV3K7IBLQRWXMR5O","created_at":"2026-07-05T11:45:36.976557+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV3K7IBL","created_at":"2026-07-05T11:45:36.976557+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/YV3K7IBLQRWXMR5OVF3GHA6S34","json":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34.json","graph_json":"https://pith.science/api/pith-number/YV3K7IBLQRWXMR5OVF3GHA6S34/graph.json","events_json":"https://pith.science/api/pith-number/YV3K7IBLQRWXMR5OVF3GHA6S34/events.json","paper":"https://pith.science/paper/YV3K7IBL"},"agent_actions":{"view_html":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34","download_json":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34.json","view_paper":"https://pith.science/paper/YV3K7IBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23349&json=true","fetch_graph":"https://pith.science/api/pith-number/YV3K7IBLQRWXMR5OVF3GHA6S34/graph.json","fetch_events":"https://pith.science/api/pith-number/YV3K7IBLQRWXMR5OVF3GHA6S34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34/action/storage_attestation","attest_author":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34/action/author_attestation","sign_citation":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34/action/citation_signature","submit_replication":"https://pith.science/pith/YV3K7IBLQRWXMR5OVF3GHA6S34/action/replication_record"}},"created_at":"2026-07-05T11:45:36.976557+00:00","updated_at":"2026-07-05T11:45:36.976557+00:00"}