{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R5G6QXBL7ZXW2WFX3TACUHNWDW","short_pith_number":"pith:R5G6QXBL","schema_version":"1.0","canonical_sha256":"8f4de85c2bfe6f6d58b7dcc02a1db61db94746e6d26191b87761af053bfca96b","source":{"kind":"arxiv","id":"2306.10577","version":3},"attestation_state":"computed","paper":{"title":"OpenDataVal: a Unified Benchmark for Data Valuation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"James Zou, Kevin Fu Jiang, Weixin Liang, Yongchan Kwon","submitted_at":"2023-06-18T14:38:29Z","abstract_excerpt":"Assessing the quality and impact of individual data points is critical for improving model performance and mitigating undesirable biases within the training dataset. Several data valuation algorithms have been proposed to quantify data quality, however, there lacks a systemic and standardized benchmarking system for data valuation. In this paper, we introduce OpenDataVal, an easy-to-use and unified benchmark framework that empowers researchers and practitioners to apply and compare various data valuation algorithms. OpenDataVal provides an integrated environment that includes (i) a diverse col"},"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":"2306.10577","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T14:38:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a5fac8354c9c710607d2a06d2c2a34cca2d2dfd3de5ecd9c868b0daef712ca20","abstract_canon_sha256":"179e05cf8bb53083edfe745a79f95b0c10f15582f3ef124740cb37eb88d41228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:24.922145Z","signature_b64":"N81rrNS1dgtJ38KAt3E5Mu9rXBO5OmiLlQ1nZWWEPEGRlQIdGmdNag4qWNvHEY01MHLA/I61Tw+g9qIyIXNyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f4de85c2bfe6f6d58b7dcc02a1db61db94746e6d26191b87761af053bfca96b","last_reissued_at":"2026-07-05T07:00:24.921609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:24.921609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenDataVal: a Unified Benchmark for Data Valuation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"James Zou, Kevin Fu Jiang, Weixin Liang, Yongchan Kwon","submitted_at":"2023-06-18T14:38:29Z","abstract_excerpt":"Assessing the quality and impact of individual data points is critical for improving model performance and mitigating undesirable biases within the training dataset. Several data valuation algorithms have been proposed to quantify data quality, however, there lacks a systemic and standardized benchmarking system for data valuation. In this paper, we introduce OpenDataVal, an easy-to-use and unified benchmark framework that empowers researchers and practitioners to apply and compare various data valuation algorithms. OpenDataVal provides an integrated environment that includes (i) a diverse col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10577","kind":"arxiv","version":3},"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/2306.10577/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":"2306.10577","created_at":"2026-07-05T07:00:24.921696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10577v3","created_at":"2026-07-05T07:00:24.921696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10577","created_at":"2026-07-05T07:00:24.921696+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5G6QXBL7ZXW","created_at":"2026-07-05T07:00:24.921696+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5G6QXBL7ZXW2WFX","created_at":"2026-07-05T07:00:24.921696+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5G6QXBL","created_at":"2026-07-05T07:00:24.921696+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12619","citing_title":"Semivalue-based data valuation is arbitrary and gameable","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW","json":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW.json","graph_json":"https://pith.science/api/pith-number/R5G6QXBL7ZXW2WFX3TACUHNWDW/graph.json","events_json":"https://pith.science/api/pith-number/R5G6QXBL7ZXW2WFX3TACUHNWDW/events.json","paper":"https://pith.science/paper/R5G6QXBL"},"agent_actions":{"view_html":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW","download_json":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW.json","view_paper":"https://pith.science/paper/R5G6QXBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10577&json=true","fetch_graph":"https://pith.science/api/pith-number/R5G6QXBL7ZXW2WFX3TACUHNWDW/graph.json","fetch_events":"https://pith.science/api/pith-number/R5G6QXBL7ZXW2WFX3TACUHNWDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW/action/storage_attestation","attest_author":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW/action/author_attestation","sign_citation":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW/action/citation_signature","submit_replication":"https://pith.science/pith/R5G6QXBL7ZXW2WFX3TACUHNWDW/action/replication_record"}},"created_at":"2026-07-05T07:00:24.921696+00:00","updated_at":"2026-07-05T07:00:24.921696+00:00"}