{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KX54OV3CUD2563IC7DBNUMC4N3","short_pith_number":"pith:KX54OV3C","schema_version":"1.0","canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","source":{"kind":"arxiv","id":"2402.17327","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"David Saulpic, David Woodruff, Kyriakos Axiotis, Michael Wunder, Monika Henzinger, Sammy Jerome, Vahab Mirrokni, Vincent Cohen-Addad","submitted_at":"2024-02-27T09:03:43Z","abstract_excerpt":"We study the data selection problem, whose aim is to select a small representative subset of data that can be used to efficiently train a machine learning model. We present a new data selection approach based on $k$-means clustering and sensitivity sampling. Assuming access to an embedding representation of the data with respect to which the model loss is H\\\"older continuous, our approach provably allows selecting a set of ``typical'' $k + 1/\\varepsilon^2$ elements whose average loss corresponds to the average loss of the whole dataset, up to a multiplicative $(1\\pm\\varepsilon)$ factor and an "},"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":"2402.17327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T09:03:43Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"8eb56bcfec1b177958d65e50d0a31256b98902764c058c7d2b2c8dd05d96c9e0","abstract_canon_sha256":"d4ebc087157faf4859e15ee4316332029fa9d1b8a7862359c42b44a533a2e0e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:45.457631Z","signature_b64":"JdOnx+iyT2BFnF/A9FipK+eNGTcp1ihCTtegK/e7TVQjFIpTATRVJEwRimad5HxcPKKtJo1iuGPz64rfHJpVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55fbc75762a0f5df6d02f8c2da305c6ed2044ff5cab660f69bf65543e6e69439","last_reissued_at":"2026-07-05T07:49:45.457144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:45.457144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"David Saulpic, David Woodruff, Kyriakos Axiotis, Michael Wunder, Monika Henzinger, Sammy Jerome, Vahab Mirrokni, Vincent Cohen-Addad","submitted_at":"2024-02-27T09:03:43Z","abstract_excerpt":"We study the data selection problem, whose aim is to select a small representative subset of data that can be used to efficiently train a machine learning model. We present a new data selection approach based on $k$-means clustering and sensitivity sampling. Assuming access to an embedding representation of the data with respect to which the model loss is H\\\"older continuous, our approach provably allows selecting a set of ``typical'' $k + 1/\\varepsilon^2$ elements whose average loss corresponds to the average loss of the whole dataset, up to a multiplicative $(1\\pm\\varepsilon)$ factor and an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17327","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/2402.17327/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":"2402.17327","created_at":"2026-07-05T07:49:45.457198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17327v1","created_at":"2026-07-05T07:49:45.457198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17327","created_at":"2026-07-05T07:49:45.457198+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX54OV3CUD25","created_at":"2026-07-05T07:49:45.457198+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX54OV3CUD2563IC","created_at":"2026-07-05T07:49:45.457198+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX54OV3C","created_at":"2026-07-05T07:49:45.457198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31131","citing_title":"Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02081","citing_title":"ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3","json":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3.json","graph_json":"https://pith.science/api/pith-number/KX54OV3CUD2563IC7DBNUMC4N3/graph.json","events_json":"https://pith.science/api/pith-number/KX54OV3CUD2563IC7DBNUMC4N3/events.json","paper":"https://pith.science/paper/KX54OV3C"},"agent_actions":{"view_html":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3","download_json":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3.json","view_paper":"https://pith.science/paper/KX54OV3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17327&json=true","fetch_graph":"https://pith.science/api/pith-number/KX54OV3CUD2563IC7DBNUMC4N3/graph.json","fetch_events":"https://pith.science/api/pith-number/KX54OV3CUD2563IC7DBNUMC4N3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/action/storage_attestation","attest_author":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/action/author_attestation","sign_citation":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/action/citation_signature","submit_replication":"https://pith.science/pith/KX54OV3CUD2563IC7DBNUMC4N3/action/replication_record"}},"created_at":"2026-07-05T07:49:45.457198+00:00","updated_at":"2026-07-05T07:49:45.457198+00:00"}