{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PKJHEZS7M3GJURLMDOFZKAZYYE","short_pith_number":"pith:PKJHEZS7","schema_version":"1.0","canonical_sha256":"7a9272665f66cc9a456c1b8b950338c1248a096fc26f84ad7de43fe4d28768ab","source":{"kind":"arxiv","id":"1707.06814","version":3},"attestation_state":"computed","paper":{"title":"Scalable and robust set similarity join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Johan Sivertsen, Rasmus Pagh, Tobias Christiani","submitted_at":"2017-07-21T09:50:36Z","abstract_excerpt":"Set similarity join is a fundamental and well-studied database operator. It is usually studied in the exact setting where the goal is to compute all pairs of sets that exceed a given similarity threshold (measured e.g. as Jaccard similarity). But set similarity join is often used in settings where 100% recall may not be important --- indeed, where the exact set similarity join is itself only an approximation of the desired result set.\n  We present a new randomized algorithm for set similarity join that can achieve any desired recall up to 100%, and show theoretically and empirically that it si"},"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":"1707.06814","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-07-21T09:50:36Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"624cc04a1d2ed95d2e675fb441535b553c44ec082dc4a0b343b78ae40d241595","abstract_canon_sha256":"33f5869fdb754baf766777054344e2c48ebcff6514d52165666d9fd6e18d5e0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:10.843070Z","signature_b64":"/CvrtbLdz+n3VGDGLIBvR8bfunrscPTFbLTxEUmD3pFDqaHjUeNEentohdCPIYmZ8h84wAOAIZ1n/3zvkSg4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a9272665f66cc9a456c1b8b950338c1248a096fc26f84ad7de43fe4d28768ab","last_reissued_at":"2026-05-18T00:22:10.842522Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:10.842522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable and robust set similarity join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Johan Sivertsen, Rasmus Pagh, Tobias Christiani","submitted_at":"2017-07-21T09:50:36Z","abstract_excerpt":"Set similarity join is a fundamental and well-studied database operator. It is usually studied in the exact setting where the goal is to compute all pairs of sets that exceed a given similarity threshold (measured e.g. as Jaccard similarity). But set similarity join is often used in settings where 100% recall may not be important --- indeed, where the exact set similarity join is itself only an approximation of the desired result set.\n  We present a new randomized algorithm for set similarity join that can achieve any desired recall up to 100%, and show theoretically and empirically that it si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06814","kind":"arxiv","version":3},"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":"1707.06814","created_at":"2026-05-18T00:22:10.842624+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.06814v3","created_at":"2026-05-18T00:22:10.842624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06814","created_at":"2026-05-18T00:22:10.842624+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKJHEZS7M3GJ","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKJHEZS7M3GJURLM","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKJHEZS7","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09430","citing_title":"Algorithms for Similarity Search and Pseudorandomness","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE","json":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE.json","graph_json":"https://pith.science/api/pith-number/PKJHEZS7M3GJURLMDOFZKAZYYE/graph.json","events_json":"https://pith.science/api/pith-number/PKJHEZS7M3GJURLMDOFZKAZYYE/events.json","paper":"https://pith.science/paper/PKJHEZS7"},"agent_actions":{"view_html":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE","download_json":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE.json","view_paper":"https://pith.science/paper/PKJHEZS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.06814&json=true","fetch_graph":"https://pith.science/api/pith-number/PKJHEZS7M3GJURLMDOFZKAZYYE/graph.json","fetch_events":"https://pith.science/api/pith-number/PKJHEZS7M3GJURLMDOFZKAZYYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/action/storage_attestation","attest_author":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/action/author_attestation","sign_citation":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/action/citation_signature","submit_replication":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/action/replication_record"}},"created_at":"2026-05-18T00:22:10.842624+00:00","updated_at":"2026-05-18T00:22:10.842624+00:00"}