{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PTN2MS36PPAZZO2ISFR5HIL2JD","short_pith_number":"pith:PTN2MS36","schema_version":"1.0","canonical_sha256":"7cdba64b7e7bc19cbb489163d3a17a48ca62be13cb9de4921c755af1ae064f63","source":{"kind":"arxiv","id":"2305.14113","version":1},"attestation_state":"computed","paper":{"title":"On the Size and Approximation Error of Distilled Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alaa Maalouf, Daniela Rus, Mathias Lechner, Murad Tukan, Noel Loo, Ramin Hasani","submitted_at":"2023-05-23T14:37:43Z","abstract_excerpt":"Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original uncompressed dataset. Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets? In this work, we take a theoretical view on kernel ridge regression (KRR) based methods of dataset distillation such as Kernel Inducing Points. B"},"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":"2305.14113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T14:37:43Z","cross_cats_sorted":[],"title_canon_sha256":"31cf7ada89ec8127d1ad360dfd2f68aabec7c3c1dcc29e2b6b4ed2f80efb23c9","abstract_canon_sha256":"f8895c04e49dcbc3380bdc629ad6857237f4f946d6da13c575025b9a4ba55584"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:01.197111Z","signature_b64":"RBsBtaI164pMT8L5WfBh22H/XqnNjvKBdoQiMt5nrnQHMAqGubGO3daFmWOisYfBgUVhA63WKTBKbxaUIkQ1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cdba64b7e7bc19cbb489163d3a17a48ca62be13cb9de4921c755af1ae064f63","last_reissued_at":"2026-07-05T06:13:01.196708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:01.196708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Size and Approximation Error of Distilled Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alaa Maalouf, Daniela Rus, Mathias Lechner, Murad Tukan, Noel Loo, Ramin Hasani","submitted_at":"2023-05-23T14:37:43Z","abstract_excerpt":"Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original uncompressed dataset. Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets? In this work, we take a theoretical view on kernel ridge regression (KRR) based methods of dataset distillation such as Kernel Inducing Points. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14113","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/2305.14113/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":"2305.14113","created_at":"2026-07-05T06:13:01.196766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14113v1","created_at":"2026-07-05T06:13:01.196766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14113","created_at":"2026-07-05T06:13:01.196766+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTN2MS36PPAZ","created_at":"2026-07-05T06:13:01.196766+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTN2MS36PPAZZO2I","created_at":"2026-07-05T06:13:01.196766+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTN2MS36","created_at":"2026-07-05T06:13:01.196766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD","json":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD.json","graph_json":"https://pith.science/api/pith-number/PTN2MS36PPAZZO2ISFR5HIL2JD/graph.json","events_json":"https://pith.science/api/pith-number/PTN2MS36PPAZZO2ISFR5HIL2JD/events.json","paper":"https://pith.science/paper/PTN2MS36"},"agent_actions":{"view_html":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD","download_json":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD.json","view_paper":"https://pith.science/paper/PTN2MS36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14113&json=true","fetch_graph":"https://pith.science/api/pith-number/PTN2MS36PPAZZO2ISFR5HIL2JD/graph.json","fetch_events":"https://pith.science/api/pith-number/PTN2MS36PPAZZO2ISFR5HIL2JD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD/action/storage_attestation","attest_author":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD/action/author_attestation","sign_citation":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD/action/citation_signature","submit_replication":"https://pith.science/pith/PTN2MS36PPAZZO2ISFR5HIL2JD/action/replication_record"}},"created_at":"2026-07-05T06:13:01.196766+00:00","updated_at":"2026-07-05T06:13:01.196766+00:00"}