{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:6JW2JWJ22QF6JW4F7TRUCAA5YP","short_pith_number":"pith:6JW2JWJ2","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"},"canonical_sha256":"f26da4d93ad40be4db85fce341001dc3d40c980dcfda7b3021b7d0ebb18789fc","source":{"kind":"arxiv","id":"1006.5235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1006.5235","created_at":"2026-05-18T03:57:27Z"},{"alias_kind":"arxiv_version","alias_value":"1006.5235v1","created_at":"2026-05-18T03:57:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1006.5235","created_at":"2026-05-18T03:57:27Z"},{"alias_kind":"pith_short_12","alias_value":"6JW2JWJ22QF6","created_at":"2026-05-18T12:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"6JW2JWJ22QF6JW4F","created_at":"2026-05-18T12:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"6JW2JWJ2","created_at":"2026-05-18T12:26:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:6JW2JWJ22QF6JW4F7TRUCAA5YP","target":"record","payload":{"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"},"canonical_sha256":"f26da4d93ad40be4db85fce341001dc3d40c980dcfda7b3021b7d0ebb18789fc","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"},"source_kind":"arxiv","source_id":"1006.5235","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:57:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtjTfZVEmezUyTvjm1X48ar24g4TxqaisXtXanwhyY4lEtGhHpuUneE6rjPz5uVgr3cSM/6UMiH8oHK+SUkCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:21:47.040655Z"},"content_sha256":"396075f1f6525fe9538278ca0506f8fed1a2eb28b6da2f26d6a0edc03207aca0","schema_version":"1.0","event_id":"sha256:396075f1f6525fe9538278ca0506f8fed1a2eb28b6da2f26d6a0edc03207aca0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:6JW2JWJ22QF6JW4F7TRUCAA5YP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:57:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"haWqKDQ1ZMiNtuEKeHNd4h8N3liKtt6so6g/br+YXAXktOoWh65vBB19TCHNmgRL7upZtmfneQ8ss1sM5Q7oDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:21:47.041004Z"},"content_sha256":"b81d5db829d5249cfefc0466a91262e353a27f806c324c5cf36e8f3f83ad4ffb","schema_version":"1.0","event_id":"sha256:b81d5db829d5249cfefc0466a91262e353a27f806c324c5cf36e8f3f83ad4ffb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/bundle.json","state_url":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T02:21:47Z","links":{"resolver":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP","bundle":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/bundle.json","state":"https://pith.science/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JW2JWJ22QF6JW4F7TRUCAA5YP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:6JW2JWJ22QF6JW4F7TRUCAA5YP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ff213035b157f5bb11eebee3bb35b599867ecbf696276ca73a6c16df57cf32ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2010-06-27T20:38:39Z","title_canon_sha256":"9bc5ad42d4fe097476a1e88142f889106ad8911a7cd37ab4016931a52dcd040d"},"schema_version":"1.0","source":{"id":"1006.5235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1006.5235","created_at":"2026-05-18T03:57:27Z"},{"alias_kind":"arxiv_version","alias_value":"1006.5235v1","created_at":"2026-05-18T03:57:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1006.5235","created_at":"2026-05-18T03:57:27Z"},{"alias_kind":"pith_short_12","alias_value":"6JW2JWJ22QF6","created_at":"2026-05-18T12:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"6JW2JWJ22QF6JW4F","created_at":"2026-05-18T12:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"6JW2JWJ2","created_at":"2026-05-18T12:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:b81d5db829d5249cfefc0466a91262e353a27f806c324c5cf36e8f3f83ad4ffb","target":"graph","created_at":"2026-05-18T03:57:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Andrea Pietracaprina, Eli Upfal, Fabio Vandin, Matteo Riondato","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2010-06-27T20:38:39Z","title":"Mining Top-K Frequent Itemsets Through Progressive Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1006.5235","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:396075f1f6525fe9538278ca0506f8fed1a2eb28b6da2f26d6a0edc03207aca0","target":"record","created_at":"2026-05-18T03:57:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ff213035b157f5bb11eebee3bb35b599867ecbf696276ca73a6c16df57cf32ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2010-06-27T20:38:39Z","title_canon_sha256":"9bc5ad42d4fe097476a1e88142f889106ad8911a7cd37ab4016931a52dcd040d"},"schema_version":"1.0","source":{"id":"1006.5235","kind":"arxiv","version":1}},"canonical_sha256":"f26da4d93ad40be4db85fce341001dc3d40c980dcfda7b3021b7d0ebb18789fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f26da4d93ad40be4db85fce341001dc3d40c980dcfda7b3021b7d0ebb18789fc","first_computed_at":"2026-05-18T03:57:27.023324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:57:27.023324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"96Ps/E68fWwClyE43OiVmkF1bg0U6em5LuRlqm3KARoJ0p/u5wUGMl66WePZEjqeHCDDnwMnoNctsyOLyLa0AA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:57:27.023992Z","signed_message":"canonical_sha256_bytes"},"source_id":"1006.5235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:396075f1f6525fe9538278ca0506f8fed1a2eb28b6da2f26d6a0edc03207aca0","sha256:b81d5db829d5249cfefc0466a91262e353a27f806c324c5cf36e8f3f83ad4ffb"],"state_sha256":"bfc1737c5becb460eae98875a349ae230d9ad5ebbae6dba8e69810d72fcc2e55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3bgEnpRPfRhvO7EKz1xb9VgnsKHrSCwhTL6ETGxgDk33UUBlagwmMa+o2Awb+YWKxSD+TOG1nb+aDtxaLP6/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T02:21:47.043053Z","bundle_sha256":"2f711fc014fe11929c81b051d4553a0601dc6af69f2ffbcbd5b7f61f2005f10a"}}