{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:6JW2JWJ22QF6JW4F7TRUCAA5YP","short_pith_number":"pith:6JW2JWJ2","schema_version":"1.0","canonical_sha256":"f26da4d93ad40be4db85fce341001dc3d40c980dcfda7b3021b7d0ebb18789fc","source":{"kind":"arxiv","id":"1006.5235","version":1},"attestation_state":"computed","paper":{"title":"Mining Top-K Frequent Itemsets Through Progressive Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Andrea Pietracaprina, Eli Upfal, Fabio Vandin, Matteo Riondato","submitted_at":"2010-06-27T20:38:39Z","abstract_excerpt":"We study the use of sampling for efficiently mining the top-K frequent itemsets of cardinality at most w. To this purpose, we define an approximation to the top-K frequent itemsets to be a family of itemsets which includes (resp., excludes) all very frequent (resp., very infrequent) itemsets, together with an estimate of these itemsets' frequencies with a bounded error. Our first result is an upper bound on the sample size which guarantees that the top-K frequent itemsets mined from a random sample of that size approximate the actual top-K frequent itemsets, with probability larger than a spec"},"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":"1006.5235","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2010-06-27T20:38:39Z","cross_cats_sorted":[],"title_canon_sha256":"9bc5ad42d4fe097476a1e88142f889106ad8911a7cd37ab4016931a52dcd040d","abstract_canon_sha256":"ff213035b157f5bb11eebee3bb35b599867ecbf696276ca73a6c16df57cf32ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:57:27.023992Z","signature_b64":"96Ps/E68fWwClyE43OiVmkF1bg0U6em5LuRlqm3KARoJ0p/u5wUGMl66WePZEjqeHCDDnwMnoNctsyOLyLa0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f26da4d93ad40be4db85fce341001dc3d40c980dcfda7b3021b7d0ebb18789fc","last_reissued_at":"2026-05-18T03:57:27.023324Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:57:27.023324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mining Top-K Frequent Itemsets Through Progressive Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Andrea Pietracaprina, Eli Upfal, Fabio Vandin, Matteo Riondato","submitted_at":"2010-06-27T20:38:39Z","abstract_excerpt":"We study the use of sampling for efficiently mining the top-K frequent itemsets of cardinality at most w. To this purpose, we define an approximation to the top-K frequent itemsets to be a family of itemsets which includes (resp., excludes) all very frequent (resp., very infrequent) itemsets, together with an estimate of these itemsets' frequencies with a bounded error. Our first result is an upper bound on the sample size which guarantees that the top-K frequent itemsets mined from a random sample of that size approximate the actual top-K frequent itemsets, with probability larger than a spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1006.5235","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":""},"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":"1006.5235","created_at":"2026-05-18T03:57:27.023417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1006.5235v1","created_at":"2026-05-18T03:57:27.023417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1006.5235","created_at":"2026-05-18T03:57:27.023417+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JW2JWJ22QF6","created_at":"2026-05-18T12:26:04.259169+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JW2JWJ22QF6JW4F","created_at":"2026-05-18T12:26:04.259169+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JW2JWJ2","created_at":"2026-05-18T12:26:04.259169+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/6JW2JWJ22QF6JW4F7TRUCAA5YP","json":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP.json","graph_json":"https://pith.science/api/pith-number/6JW2JWJ22QF6JW4F7TRUCAA5YP/graph.json","events_json":"https://pith.science/api/pith-number/6JW2JWJ22QF6JW4F7TRUCAA5YP/events.json","paper":"https://pith.science/paper/6JW2JWJ2"},"agent_actions":{"view_html":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP","download_json":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP.json","view_paper":"https://pith.science/paper/6JW2JWJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1006.5235&json=true","fetch_graph":"https://pith.science/api/pith-number/6JW2JWJ22QF6JW4F7TRUCAA5YP/graph.json","fetch_events":"https://pith.science/api/pith-number/6JW2JWJ22QF6JW4F7TRUCAA5YP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/action/storage_attestation","attest_author":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/action/author_attestation","sign_citation":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/action/citation_signature","submit_replication":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/action/replication_record"}},"created_at":"2026-05-18T03:57:27.023417+00:00","updated_at":"2026-05-18T03:57:27.023417+00:00"}