{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QEDO5S4C6ONVWFLP77PN6GCLGL","short_pith_number":"pith:QEDO5S4C","schema_version":"1.0","canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","source":{"kind":"arxiv","id":"1703.06476","version":2},"attestation_state":"computed","paper":{"title":"Practical Coreset Constructions for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem","submitted_at":"2017-03-19T17:45:29Z","abstract_excerpt":"We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set. We provide an overview over the state-of-the-art in coreset construction for machine learning. In Section 2, we present both the intuition behind and a theoretically sound framework to construct coresets for general problems and apply it to $k$-means clustering. In Section 3 we summarize existing coreset construction algorithms for a variety of machine learning problems such as maximum likelihood estimation of mixture"},"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":"1703.06476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-19T17:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"ededf2c4a708900f4113512098a9263133553938d21848c20ef9e7df241ec83e","abstract_canon_sha256":"59924536c83025bd584f7bd5b8002f661ec8f84129267fe2d0d96b676e71bd9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:08.470898Z","signature_b64":"8N75gOrnP7sXPnnPmAlTCNLdjMm3b8UrB3BT76n5Styw1f7s3aqZ+k3jrBbKfrvaUyUZgK6cP+kzsn4j3KbEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8106eecb82f39b5b156fffdedf184b32c06232e2bab5029dbe5304cedda30d95","last_reissued_at":"2026-05-18T00:43:08.470267Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:08.470267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Coreset Constructions for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem","submitted_at":"2017-03-19T17:45:29Z","abstract_excerpt":"We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set. We provide an overview over the state-of-the-art in coreset construction for machine learning. In Section 2, we present both the intuition behind and a theoretically sound framework to construct coresets for general problems and apply it to $k$-means clustering. In Section 3 we summarize existing coreset construction algorithms for a variety of machine learning problems such as maximum likelihood estimation of mixture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06476","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":""},"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":"1703.06476","created_at":"2026-05-18T00:43:08.470355+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.06476v2","created_at":"2026-05-18T00:43:08.470355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06476","created_at":"2026-05-18T00:43:08.470355+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEDO5S4C6ONV","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEDO5S4C6ONVWFLP","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEDO5S4C","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2310.14768","citing_title":"Policy Gradient with Kernel Quadrature","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1811.10959","citing_title":"Dataset Distillation","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20754","citing_title":"Stationary MMD Points","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02081","citing_title":"ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12317","citing_title":"Check, Please: Verifiably Fair Clustering","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL","json":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL.json","graph_json":"https://pith.science/api/pith-number/QEDO5S4C6ONVWFLP77PN6GCLGL/graph.json","events_json":"https://pith.science/api/pith-number/QEDO5S4C6ONVWFLP77PN6GCLGL/events.json","paper":"https://pith.science/paper/QEDO5S4C"},"agent_actions":{"view_html":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL","download_json":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL.json","view_paper":"https://pith.science/paper/QEDO5S4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.06476&json=true","fetch_graph":"https://pith.science/api/pith-number/QEDO5S4C6ONVWFLP77PN6GCLGL/graph.json","fetch_events":"https://pith.science/api/pith-number/QEDO5S4C6ONVWFLP77PN6GCLGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/action/storage_attestation","attest_author":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/action/author_attestation","sign_citation":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/action/citation_signature","submit_replication":"https://pith.science/pith/QEDO5S4C6ONVWFLP77PN6GCLGL/action/replication_record"}},"created_at":"2026-05-18T00:43:08.470355+00:00","updated_at":"2026-05-18T00:43:08.470355+00:00"}