{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VOBGZZUCTK2OFFTQI2HDHMMBIQ","short_pith_number":"pith:VOBGZZUC","schema_version":"1.0","canonical_sha256":"ab826ce6829ab4e29670468e33b181440aa49164a3a21cd7a4ec3da2f38b8633","source":{"kind":"arxiv","id":"2406.01130","version":2},"attestation_state":"computed","paper":{"title":"SAVA: Scalable Learning-Agnostic Data Valuation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Samuel Kessler, Tam Le, Vu Nguyen","submitted_at":"2024-06-03T09:17:35Z","abstract_excerpt":"Selecting data for training machine learning models is crucial since large, web-scraped, real datasets contain noisy artifacts that affect the quality and relevance of individual data points. These noisy artifacts will impact model performance. We formulate this problem as a data valuation task, assigning a value to data points in the training set according to how similar or dissimilar they are to a clean and curated validation set. Recently, LAVA demonstrated the use of optimal transport (OT) between a large noisy training dataset and a clean validation set, to value training data efficiently"},"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":"2406.01130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T09:17:35Z","cross_cats_sorted":[],"title_canon_sha256":"0f9e4ad38bd46621034d0c56156a3154d4d53154608f456d6de3f4e96cd434b7","abstract_canon_sha256":"39be753304bbf41c34b9d01d380c0d7e0f829a386d1768ac42f88b7a65a6ab7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:37.979150Z","signature_b64":"dOjdfl6js/5zf7HvurIbGfP17bl5PxrF+P+gje4njdryDoo/x5OS+zdUgO2+AsOQzkTgqfidccA9yfTMTNjnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab826ce6829ab4e29670468e33b181440aa49164a3a21cd7a4ec3da2f38b8633","last_reissued_at":"2026-07-05T10:34:37.978480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:37.978480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAVA: Scalable Learning-Agnostic Data Valuation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Samuel Kessler, Tam Le, Vu Nguyen","submitted_at":"2024-06-03T09:17:35Z","abstract_excerpt":"Selecting data for training machine learning models is crucial since large, web-scraped, real datasets contain noisy artifacts that affect the quality and relevance of individual data points. These noisy artifacts will impact model performance. We formulate this problem as a data valuation task, assigning a value to data points in the training set according to how similar or dissimilar they are to a clean and curated validation set. Recently, LAVA demonstrated the use of optimal transport (OT) between a large noisy training dataset and a clean validation set, to value training data efficiently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01130","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/2406.01130/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":"2406.01130","created_at":"2026-07-05T10:34:37.978558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01130v2","created_at":"2026-07-05T10:34:37.978558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01130","created_at":"2026-07-05T10:34:37.978558+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOBGZZUCTK2O","created_at":"2026-07-05T10:34:37.978558+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOBGZZUCTK2OFFTQ","created_at":"2026-07-05T10:34:37.978558+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOBGZZUC","created_at":"2026-07-05T10:34:37.978558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23799","citing_title":"KAIROS: Scalable Model-Agnostic Data Valuation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ","json":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ.json","graph_json":"https://pith.science/api/pith-number/VOBGZZUCTK2OFFTQI2HDHMMBIQ/graph.json","events_json":"https://pith.science/api/pith-number/VOBGZZUCTK2OFFTQI2HDHMMBIQ/events.json","paper":"https://pith.science/paper/VOBGZZUC"},"agent_actions":{"view_html":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ","download_json":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ.json","view_paper":"https://pith.science/paper/VOBGZZUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01130&json=true","fetch_graph":"https://pith.science/api/pith-number/VOBGZZUCTK2OFFTQI2HDHMMBIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VOBGZZUCTK2OFFTQI2HDHMMBIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ/action/storage_attestation","attest_author":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ/action/author_attestation","sign_citation":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ/action/citation_signature","submit_replication":"https://pith.science/pith/VOBGZZUCTK2OFFTQI2HDHMMBIQ/action/replication_record"}},"created_at":"2026-07-05T10:34:37.978558+00:00","updated_at":"2026-07-05T10:34:37.978558+00:00"}