{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SJAG4ORQUA64FD336B5XJQ5TAY","short_pith_number":"pith:SJAG4ORQ","schema_version":"1.0","canonical_sha256":"92406e3a30a03dc28f7bf07b74c3b3061269cc93f1478a0b6dfb6e46f9373e2a","source":{"kind":"arxiv","id":"2002.06469","version":1},"attestation_state":"computed","paper":{"title":"On Coresets for Support Vector Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Murad Tukan","submitted_at":"2020-02-15T23:25:12Z","abstract_excerpt":"We present an efficient coreset construction algorithm for large-scale Support Vector Machine (SVM) training in Big Data and streaming applications. A coreset is a small, representative subset of the original data points such that a models trained on the coreset are provably competitive with those trained on the original data set. Since the size of the coreset is generally much smaller than the original set, our preprocess-then-train scheme has potential to lead to significant speedups when training SVM models. We prove lower and upper bounds on the size of the coreset required to obtain small"},"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":"2002.06469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:25:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0f48080e95b7eb4f3f8f0b5e546aa71ef6361d5699e235b1867e756b51e11c7c","abstract_canon_sha256":"9196990c08d76a347561d6f1d167586edda6757461c36c289247684bb9b9bf86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:06.443280Z","signature_b64":"YFMq11ZGHpj94P1bbQnVNWdoDwU9WO2n0K8FokL5wa072DdoAqaozEED8g/TXzkWdCoiqOUe9YXxfhxQszS5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92406e3a30a03dc28f7bf07b74c3b3061269cc93f1478a0b6dfb6e46f9373e2a","last_reissued_at":"2026-07-05T00:41:06.442805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:06.442805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Coresets for Support Vector Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Murad Tukan","submitted_at":"2020-02-15T23:25:12Z","abstract_excerpt":"We present an efficient coreset construction algorithm for large-scale Support Vector Machine (SVM) training in Big Data and streaming applications. A coreset is a small, representative subset of the original data points such that a models trained on the coreset are provably competitive with those trained on the original data set. Since the size of the coreset is generally much smaller than the original set, our preprocess-then-train scheme has potential to lead to significant speedups when training SVM models. We prove lower and upper bounds on the size of the coreset required to obtain small"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06469","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/2002.06469/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":"2002.06469","created_at":"2026-07-05T00:41:06.442877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06469v1","created_at":"2026-07-05T00:41:06.442877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06469","created_at":"2026-07-05T00:41:06.442877+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJAG4ORQUA64","created_at":"2026-07-05T00:41:06.442877+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJAG4ORQUA64FD33","created_at":"2026-07-05T00:41:06.442877+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJAG4ORQ","created_at":"2026-07-05T00:41:06.442877+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/SJAG4ORQUA64FD336B5XJQ5TAY","json":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY.json","graph_json":"https://pith.science/api/pith-number/SJAG4ORQUA64FD336B5XJQ5TAY/graph.json","events_json":"https://pith.science/api/pith-number/SJAG4ORQUA64FD336B5XJQ5TAY/events.json","paper":"https://pith.science/paper/SJAG4ORQ"},"agent_actions":{"view_html":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY","download_json":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY.json","view_paper":"https://pith.science/paper/SJAG4ORQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06469&json=true","fetch_graph":"https://pith.science/api/pith-number/SJAG4ORQUA64FD336B5XJQ5TAY/graph.json","fetch_events":"https://pith.science/api/pith-number/SJAG4ORQUA64FD336B5XJQ5TAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY/action/storage_attestation","attest_author":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY/action/author_attestation","sign_citation":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY/action/citation_signature","submit_replication":"https://pith.science/pith/SJAG4ORQUA64FD336B5XJQ5TAY/action/replication_record"}},"created_at":"2026-07-05T00:41:06.442877+00:00","updated_at":"2026-07-05T00:41:06.442877+00:00"}