{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VOBGZZUCTK2OFFTQI2HDHMMBIQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"39be753304bbf41c34b9d01d380c0d7e0f829a386d1768ac42f88b7a65a6ab7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T09:17:35Z","title_canon_sha256":"0f9e4ad38bd46621034d0c56156a3154d4d53154608f456d6de3f4e96cd434b7"},"schema_version":"1.0","source":{"id":"2406.01130","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01130","created_at":"2026-07-05T10:34:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01130v2","created_at":"2026-07-05T10:34:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01130","created_at":"2026-07-05T10:34:37Z"},{"alias_kind":"pith_short_12","alias_value":"VOBGZZUCTK2O","created_at":"2026-07-05T10:34:37Z"},{"alias_kind":"pith_short_16","alias_value":"VOBGZZUCTK2OFFTQ","created_at":"2026-07-05T10:34:37Z"},{"alias_kind":"pith_short_8","alias_value":"VOBGZZUC","created_at":"2026-07-05T10:34:37Z"}],"graph_snapshots":[{"event_id":"sha256:6681aed68f6f00c6f952c32ba8b357046bb71e29b61dfd1aea2e147e194e1c75","target":"graph","created_at":"2026-07-05T10:34:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.01130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Samuel Kessler, Tam Le, Vu Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T09:17:35Z","title":"SAVA: Scalable Learning-Agnostic Data Valuation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01130","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a7c826af1f1c1a0a6bbab103f19a91f2ce7e690d90b4b7bd25cff095baed43b1","target":"record","created_at":"2026-07-05T10:34:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"39be753304bbf41c34b9d01d380c0d7e0f829a386d1768ac42f88b7a65a6ab7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T09:17:35Z","title_canon_sha256":"0f9e4ad38bd46621034d0c56156a3154d4d53154608f456d6de3f4e96cd434b7"},"schema_version":"1.0","source":{"id":"2406.01130","kind":"arxiv","version":2}},"canonical_sha256":"ab826ce6829ab4e29670468e33b181440aa49164a3a21cd7a4ec3da2f38b8633","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab826ce6829ab4e29670468e33b181440aa49164a3a21cd7a4ec3da2f38b8633","first_computed_at":"2026-07-05T10:34:37.978480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:37.978480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOjdfl6js/5zf7HvurIbGfP17bl5PxrF+P+gje4njdryDoo/x5OS+zdUgO2+AsOQzkTgqfidccA9yfTMTNjnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:37.979150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01130","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7c826af1f1c1a0a6bbab103f19a91f2ce7e690d90b4b7bd25cff095baed43b1","sha256:6681aed68f6f00c6f952c32ba8b357046bb71e29b61dfd1aea2e147e194e1c75"],"state_sha256":"aa13d0a262b09dad834ce87d7f3d07b2ce3b4a9e8ab484bc76fb7e5586ad95ff"}