{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4GGOU4PRCC3UQDETOQFKVQMNOL","short_pith_number":"pith:4GGOU4PR","schema_version":"1.0","canonical_sha256":"e18cea71f110b7480c93740aaac18d72f5677a429599e601767a971a49919eaa","source":{"kind":"arxiv","id":"2009.06192","version":1},"attestation_state":"computed","paper":{"title":"A Principled Approach to Data Valuation for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ce Zhang, Dawn Song, Johannes Rausch, Ruoxi Jia, Tianhao Wang","submitted_at":"2020-09-14T04:37:54Z","abstract_excerpt":"Federated learning (FL) is a popular technique to train machine learning (ML) models on decentralized data sources. In order to sustain long-term participation of data owners, it is important to fairly appraise each data source and compensate data owners for their contribution to the training process. The Shapley value (SV) defines a unique payoff scheme that satisfies many desiderata for a data value notion. It has been increasingly used for valuing training data in centralized learning. However, computing the SV requires exhaustively evaluating the model performance on every subset of data s"},"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":"2009.06192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T04:37:54Z","cross_cats_sorted":["cs.CY","stat.ML"],"title_canon_sha256":"322ec59aa5e7ec4cb13671f51a11b6758e7cfc4e0a9c5afb2bd372a1e88bcfd3","abstract_canon_sha256":"e785ce8ccdff69a57f19c3525de6c304b3a843253b6389aeb220a8708cdd6136"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:06.051982Z","signature_b64":"SHY4ptSPQcQs7k8/m+A0YIXRUGALF/iiRarI7nJJ/wLKf2NiOIHpPz8PTc4BUJC3qwYZ4ca4FA60u4pis3L3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e18cea71f110b7480c93740aaac18d72f5677a429599e601767a971a49919eaa","last_reissued_at":"2026-07-05T01:35:06.051576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:06.051576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Principled Approach to Data Valuation for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ce Zhang, Dawn Song, Johannes Rausch, Ruoxi Jia, Tianhao Wang","submitted_at":"2020-09-14T04:37:54Z","abstract_excerpt":"Federated learning (FL) is a popular technique to train machine learning (ML) models on decentralized data sources. In order to sustain long-term participation of data owners, it is important to fairly appraise each data source and compensate data owners for their contribution to the training process. The Shapley value (SV) defines a unique payoff scheme that satisfies many desiderata for a data value notion. It has been increasingly used for valuing training data in centralized learning. However, computing the SV requires exhaustively evaluating the model performance on every subset of data s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06192","kind":"arxiv","version":1},"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/2009.06192/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":"2009.06192","created_at":"2026-07-05T01:35:06.051634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.06192v1","created_at":"2026-07-05T01:35:06.051634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06192","created_at":"2026-07-05T01:35:06.051634+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GGOU4PRCC3U","created_at":"2026-07-05T01:35:06.051634+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GGOU4PRCC3UQDET","created_at":"2026-07-05T01:35:06.051634+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GGOU4PR","created_at":"2026-07-05T01:35:06.051634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23426","citing_title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL","json":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL.json","graph_json":"https://pith.science/api/pith-number/4GGOU4PRCC3UQDETOQFKVQMNOL/graph.json","events_json":"https://pith.science/api/pith-number/4GGOU4PRCC3UQDETOQFKVQMNOL/events.json","paper":"https://pith.science/paper/4GGOU4PR"},"agent_actions":{"view_html":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL","download_json":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL.json","view_paper":"https://pith.science/paper/4GGOU4PR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.06192&json=true","fetch_graph":"https://pith.science/api/pith-number/4GGOU4PRCC3UQDETOQFKVQMNOL/graph.json","fetch_events":"https://pith.science/api/pith-number/4GGOU4PRCC3UQDETOQFKVQMNOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL/action/storage_attestation","attest_author":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL/action/author_attestation","sign_citation":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL/action/citation_signature","submit_replication":"https://pith.science/pith/4GGOU4PRCC3UQDETOQFKVQMNOL/action/replication_record"}},"created_at":"2026-07-05T01:35:06.051634+00:00","updated_at":"2026-07-05T01:35:06.051634+00:00"}