{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OHW2QTGLV34OF7QJLNB2746755","short_pith_number":"pith:OHW2QTGL","schema_version":"1.0","canonical_sha256":"71eda84ccbaef8e2fe095b43aff3dfef5f21977b9e9644f4bada7676d1b86344","source":{"kind":"arxiv","id":"2406.11011","version":3},"attestation_state":"computed","paper":{"title":"Data Shapley in One Training Run","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawn Song, Jiachen T. Wang, Prateek Mittal, Ruoxi Jia","submitted_at":"2024-06-16T17:09:24Z","abstract_excerpt":"Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts. However, existing approaches require re-training models on different data subsets, which is computationally intensive, foreclosing their application to large-scale models. Furthermore, they produce the same attribution score for any models produced by running the learning algorithm, meaning they cannot perform targeted attribution towards a specific model obtained from a single run of the algorithm. This paper introduces In-Run Data Shapley, which addresses these limitations by of"},"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":"2406.11011","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-16T17:09:24Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"760aef57d4335cb1b1cc2e75053aa42a398a57364776bf74c9579bcd72e7401b","abstract_canon_sha256":"2e78c9e82b0caf8d9385e26f5fa3189dab09f9c1ac360a2c57d366110d176c2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:33.442660Z","signature_b64":"nqvWGjoJm0uD9Ka9JrTY0XG/baltjY+VQTIH36FELas/YwEGNq/c5PYXY0aJvYl1TRX6Rx7uVWgTF2+k09PQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71eda84ccbaef8e2fe095b43aff3dfef5f21977b9e9644f4bada7676d1b86344","last_reissued_at":"2026-07-05T11:17:33.442169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:33.442169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Shapley in One Training Run","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawn Song, Jiachen T. Wang, Prateek Mittal, Ruoxi Jia","submitted_at":"2024-06-16T17:09:24Z","abstract_excerpt":"Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts. However, existing approaches require re-training models on different data subsets, which is computationally intensive, foreclosing their application to large-scale models. Furthermore, they produce the same attribution score for any models produced by running the learning algorithm, meaning they cannot perform targeted attribution towards a specific model obtained from a single run of the algorithm. This paper introduces In-Run Data Shapley, which addresses these limitations by of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11011","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/2406.11011/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":"2406.11011","created_at":"2026-07-05T11:17:33.442226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11011v3","created_at":"2026-07-05T11:17:33.442226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11011","created_at":"2026-07-05T11:17:33.442226+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHW2QTGLV34O","created_at":"2026-07-05T11:17:33.442226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHW2QTGLV34OF7QJ","created_at":"2026-07-05T11:17:33.442226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHW2QTGL","created_at":"2026-07-05T11:17:33.442226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30462","citing_title":"idSCD: Identifying Training Datasets through Semantic Correlation Descriptors","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15520","citing_title":"On the Fragility of Data Attribution When Learning Is Distributed","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06920","citing_title":"In-Context Credit Assignment via the Core","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755","json":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755.json","graph_json":"https://pith.science/api/pith-number/OHW2QTGLV34OF7QJLNB2746755/graph.json","events_json":"https://pith.science/api/pith-number/OHW2QTGLV34OF7QJLNB2746755/events.json","paper":"https://pith.science/paper/OHW2QTGL"},"agent_actions":{"view_html":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755","download_json":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755.json","view_paper":"https://pith.science/paper/OHW2QTGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11011&json=true","fetch_graph":"https://pith.science/api/pith-number/OHW2QTGLV34OF7QJLNB2746755/graph.json","fetch_events":"https://pith.science/api/pith-number/OHW2QTGLV34OF7QJLNB2746755/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755/action/storage_attestation","attest_author":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755/action/author_attestation","sign_citation":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755/action/citation_signature","submit_replication":"https://pith.science/pith/OHW2QTGLV34OF7QJLNB2746755/action/replication_record"}},"created_at":"2026-07-05T11:17:33.442226+00:00","updated_at":"2026-07-05T11:17:33.442226+00:00"}