{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMZEDFDPDXOCV7Z2EWD6ZLXNGW","short_pith_number":"pith:WMZEDFDP","schema_version":"1.0","canonical_sha256":"b33241946f1ddc2aff3a2587ecaeed35ad4b51d282ef8042eaeff2fe156c87f4","source":{"kind":"arxiv","id":"2403.13893","version":2},"attestation_state":"computed","paper":{"title":"DAVED: Data Acquisition via Experimental Design for Data Markets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baihe Huang, Charles Lu, Michael Jordan, Praneeth Vepakomma, Ramesh Raskar, Sai Praneeth Karimireddy","submitted_at":"2024-03-20T18:05:52Z","abstract_excerpt":"The acquisition of training data is crucial for machine learning applications. Data markets can increase the supply of data, particularly in data-scarce domains such as healthcare, by incentivizing potential data providers to join the market. A major challenge for a data buyer in such a market is choosing the most valuable data points from a data seller. Unlike prior work in data valuation, which assumes centralized data access, we propose a federated approach to the data acquisition problem that is inspired by linear experimental design. Our proposed data acquisition method achieves lower pre"},"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":"2403.13893","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-20T18:05:52Z","cross_cats_sorted":[],"title_canon_sha256":"47fbe8ac0c9d345a42a9fd5eb2a7ebb19f463ff26085943e27e6ebdd5fcf2c17","abstract_canon_sha256":"1320bff2bf33dcf21500432f1638264875203a15a8f2ae92e5c2250d32b05be8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:00.513706Z","signature_b64":"naw/v7PujaZYBxFrU88qnBC1hDBvbpfREjkbCaBy4GNqblG1IZ8ZV11R+RrJsnpT9xCXHFq0+Mtps76D/8rfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33241946f1ddc2aff3a2587ecaeed35ad4b51d282ef8042eaeff2fe156c87f4","last_reissued_at":"2026-07-05T09:13:00.513235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:00.513235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAVED: Data Acquisition via Experimental Design for Data Markets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baihe Huang, Charles Lu, Michael Jordan, Praneeth Vepakomma, Ramesh Raskar, Sai Praneeth Karimireddy","submitted_at":"2024-03-20T18:05:52Z","abstract_excerpt":"The acquisition of training data is crucial for machine learning applications. Data markets can increase the supply of data, particularly in data-scarce domains such as healthcare, by incentivizing potential data providers to join the market. A major challenge for a data buyer in such a market is choosing the most valuable data points from a data seller. Unlike prior work in data valuation, which assumes centralized data access, we propose a federated approach to the data acquisition problem that is inspired by linear experimental design. Our proposed data acquisition method achieves lower pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13893","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/2403.13893/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":"2403.13893","created_at":"2026-07-05T09:13:00.513289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13893v2","created_at":"2026-07-05T09:13:00.513289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13893","created_at":"2026-07-05T09:13:00.513289+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMZEDFDPDXOC","created_at":"2026-07-05T09:13:00.513289+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMZEDFDPDXOCV7Z2","created_at":"2026-07-05T09:13:00.513289+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMZEDFDP","created_at":"2026-07-05T09:13:00.513289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08821","citing_title":"Buying Data of Unknown Quality: Fisher Information Procurement Auctions","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW","json":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW.json","graph_json":"https://pith.science/api/pith-number/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/graph.json","events_json":"https://pith.science/api/pith-number/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/events.json","paper":"https://pith.science/paper/WMZEDFDP"},"agent_actions":{"view_html":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW","download_json":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW.json","view_paper":"https://pith.science/paper/WMZEDFDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13893&json=true","fetch_graph":"https://pith.science/api/pith-number/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/graph.json","fetch_events":"https://pith.science/api/pith-number/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/action/storage_attestation","attest_author":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/action/author_attestation","sign_citation":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/action/citation_signature","submit_replication":"https://pith.science/pith/WMZEDFDPDXOCV7Z2EWD6ZLXNGW/action/replication_record"}},"created_at":"2026-07-05T09:13:00.513289+00:00","updated_at":"2026-07-05T09:13:00.513289+00:00"}