{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WELO32SK2R3A6LAFGDAH5UHWMM","short_pith_number":"pith:WELO32SK","schema_version":"1.0","canonical_sha256":"b116edea4ad4760f2c0530c07ed0f6630a28f32e0fcdc0e220171073f9bd3ed4","source":{"kind":"arxiv","id":"2606.17316","version":1},"attestation_state":"computed","paper":{"title":"Approximation Preserving Coresets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Chris Schwiegelshohn, Milind Prabhu, Sudarshan Shyam","submitted_at":"2026-06-15T21:48:03Z","abstract_excerpt":"Clustering in a big data setting is an intensively studied problem, with coresets emerging as one of the important paradigms in this line of work. Given a cost function $\\text{cost}(P,S)$ mapping input points $P$ and a solution $S$ to an objective value, a coreset is a typically weighted sketch $\\Omega\\subseteq P$ such that $\\text{cost}(\\Omega,S)\\approx \\text{cost}(P,S)$. In practice, coreset sizes much smaller than those suggested by theoretical guarantees are often found to be sufficient.\n  In this paper, we offer an explanation for this phenomenon. Smaller coreset sizes suffice if we only w"},"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":"2606.17316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2026-06-15T21:48:03Z","cross_cats_sorted":[],"title_canon_sha256":"5ef4d6754bf80e8b9c32911302fee62b5914bb8ae77dc38e2d24a55b8a68d097","abstract_canon_sha256":"9143fdde3eb0de9594fcd55e6663523e42dbfc78f15cefbb3fa2dc2895c4792d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:08.831080Z","signature_b64":"lyWFzi8d3TcY6X3RToFVDNmg/EmXxwQEhYTm8ZxiMDjuyS2mbHj3JvsWe6QbRdNtXvZhPWD35xRy67W+eTjsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b116edea4ad4760f2c0530c07ed0f6630a28f32e0fcdc0e220171073f9bd3ed4","last_reissued_at":"2026-06-19T16:10:08.830736Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:08.830736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation Preserving Coresets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Chris Schwiegelshohn, Milind Prabhu, Sudarshan Shyam","submitted_at":"2026-06-15T21:48:03Z","abstract_excerpt":"Clustering in a big data setting is an intensively studied problem, with coresets emerging as one of the important paradigms in this line of work. Given a cost function $\\text{cost}(P,S)$ mapping input points $P$ and a solution $S$ to an objective value, a coreset is a typically weighted sketch $\\Omega\\subseteq P$ such that $\\text{cost}(\\Omega,S)\\approx \\text{cost}(P,S)$. In practice, coreset sizes much smaller than those suggested by theoretical guarantees are often found to be sufficient.\n  In this paper, we offer an explanation for this phenomenon. Smaller coreset sizes suffice if we only w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17316","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/2606.17316/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":"2606.17316","created_at":"2026-06-19T16:10:08.830797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17316v1","created_at":"2026-06-19T16:10:08.830797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17316","created_at":"2026-06-19T16:10:08.830797+00:00"},{"alias_kind":"pith_short_12","alias_value":"WELO32SK2R3A","created_at":"2026-06-19T16:10:08.830797+00:00"},{"alias_kind":"pith_short_16","alias_value":"WELO32SK2R3A6LAF","created_at":"2026-06-19T16:10:08.830797+00:00"},{"alias_kind":"pith_short_8","alias_value":"WELO32SK","created_at":"2026-06-19T16:10:08.830797+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/WELO32SK2R3A6LAFGDAH5UHWMM","json":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM.json","graph_json":"https://pith.science/api/pith-number/WELO32SK2R3A6LAFGDAH5UHWMM/graph.json","events_json":"https://pith.science/api/pith-number/WELO32SK2R3A6LAFGDAH5UHWMM/events.json","paper":"https://pith.science/paper/WELO32SK"},"agent_actions":{"view_html":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM","download_json":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM.json","view_paper":"https://pith.science/paper/WELO32SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17316&json=true","fetch_graph":"https://pith.science/api/pith-number/WELO32SK2R3A6LAFGDAH5UHWMM/graph.json","fetch_events":"https://pith.science/api/pith-number/WELO32SK2R3A6LAFGDAH5UHWMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM/action/storage_attestation","attest_author":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM/action/author_attestation","sign_citation":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM/action/citation_signature","submit_replication":"https://pith.science/pith/WELO32SK2R3A6LAFGDAH5UHWMM/action/replication_record"}},"created_at":"2026-06-19T16:10:08.830797+00:00","updated_at":"2026-06-19T16:10:08.830797+00:00"}