{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PCLIOAOSAR7XGOGXYAD3EJQBRA","short_pith_number":"pith:PCLIOAOS","schema_version":"1.0","canonical_sha256":"78968701d2047f7338d7c007b2260188146b39dffb9d7620cf3911681dcb93c8","source":{"kind":"arxiv","id":"1708.05159","version":2},"attestation_state":"computed","paper":{"title":"Finding Subcube Heavy Hitters in Analytics Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Branislav Kveton, Hoa T. Vu, S. Muthukrishnan, Yikun Xian","submitted_at":"2017-08-17T07:37:51Z","abstract_excerpt":"Data streams typically have items of large number of dimensions. We study the fundamental heavy-hitters problem in this setting. Formally, the data stream consists of $d$-dimensional items $x_1,\\ldots,x_m \\in [n]^d$. A $k$-dimensional subcube $T$ is a subset of distinct coordinates $\\{ T_1,\\cdots,T_k \\} \\subseteq [d]$. A subcube heavy hitter query ${\\rm Query}(T,v)$, $v \\in [n]^k$, outputs YES if $f_T(v) \\geq \\gamma$ and NO if $f_T(v) < \\gamma/4$, where $f_T$ is the ratio of number of stream items whose coordinates $T$ have joint values $v$. The all subcube heavy hitters query ${\\rm AllQuery}("},"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":"1708.05159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-08-17T07:37:51Z","cross_cats_sorted":[],"title_canon_sha256":"0a906aae4a386bfa1a28e1563426e866b7058104d620d50d9a5edac66b841253","abstract_canon_sha256":"10e187f5c4d8643462d99df5da8f432b8c4ed5bb06b2c2c1dc97ffe0904fc55c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:52.687453Z","signature_b64":"D8ah0tQgd47JcNFuVWOjC3YbuK0ENXWgjM3RGe4Awa0Etgp5E7urDLlDSLKUzfTyD7TOActjfyo/7snU3VO+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78968701d2047f7338d7c007b2260188146b39dffb9d7620cf3911681dcb93c8","last_reissued_at":"2026-05-18T00:22:52.686926Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:52.686926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Subcube Heavy Hitters in Analytics Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Branislav Kveton, Hoa T. Vu, S. Muthukrishnan, Yikun Xian","submitted_at":"2017-08-17T07:37:51Z","abstract_excerpt":"Data streams typically have items of large number of dimensions. We study the fundamental heavy-hitters problem in this setting. Formally, the data stream consists of $d$-dimensional items $x_1,\\ldots,x_m \\in [n]^d$. A $k$-dimensional subcube $T$ is a subset of distinct coordinates $\\{ T_1,\\cdots,T_k \\} \\subseteq [d]$. A subcube heavy hitter query ${\\rm Query}(T,v)$, $v \\in [n]^k$, outputs YES if $f_T(v) \\geq \\gamma$ and NO if $f_T(v) < \\gamma/4$, where $f_T$ is the ratio of number of stream items whose coordinates $T$ have joint values $v$. The all subcube heavy hitters query ${\\rm AllQuery}("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05159","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":"1708.05159","created_at":"2026-05-18T00:22:52.687000+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05159v2","created_at":"2026-05-18T00:22:52.687000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05159","created_at":"2026-05-18T00:22:52.687000+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCLIOAOSAR7X","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCLIOAOSAR7XGOGX","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCLIOAOS","created_at":"2026-05-18T12:31:37.085036+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/PCLIOAOSAR7XGOGXYAD3EJQBRA","json":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA.json","graph_json":"https://pith.science/api/pith-number/PCLIOAOSAR7XGOGXYAD3EJQBRA/graph.json","events_json":"https://pith.science/api/pith-number/PCLIOAOSAR7XGOGXYAD3EJQBRA/events.json","paper":"https://pith.science/paper/PCLIOAOS"},"agent_actions":{"view_html":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA","download_json":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA.json","view_paper":"https://pith.science/paper/PCLIOAOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05159&json=true","fetch_graph":"https://pith.science/api/pith-number/PCLIOAOSAR7XGOGXYAD3EJQBRA/graph.json","fetch_events":"https://pith.science/api/pith-number/PCLIOAOSAR7XGOGXYAD3EJQBRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA/action/storage_attestation","attest_author":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA/action/author_attestation","sign_citation":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA/action/citation_signature","submit_replication":"https://pith.science/pith/PCLIOAOSAR7XGOGXYAD3EJQBRA/action/replication_record"}},"created_at":"2026-05-18T00:22:52.687000+00:00","updated_at":"2026-05-18T00:22:52.687000+00:00"}