{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PKJHEZS7M3GJURLMDOFZKAZYYE","short_pith_number":"pith:PKJHEZS7","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"},"canonical_sha256":"7a9272665f66cc9a456c1b8b950338c1248a096fc26f84ad7de43fe4d28768ab","source":{"kind":"arxiv","id":"1707.06814","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06814","created_at":"2026-05-18T00:22:10Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06814v3","created_at":"2026-05-18T00:22:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06814","created_at":"2026-05-18T00:22:10Z"},{"alias_kind":"pith_short_12","alias_value":"PKJHEZS7M3GJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PKJHEZS7M3GJURLM","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PKJHEZS7","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PKJHEZS7M3GJURLMDOFZKAZYYE","target":"record","payload":{"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"},"canonical_sha256":"7a9272665f66cc9a456c1b8b950338c1248a096fc26f84ad7de43fe4d28768ab","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"},"source_kind":"arxiv","source_id":"1707.06814","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yj2vlBq7JAsQYUkiqmkQh1s0MJ5WCjAA7Kp0Gnu452tMM4cIsJvwwbxX06QZ6Ai8J5dqhYtS5XLu7X3hRoTHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:15:15.978159Z"},"content_sha256":"60795892fe858b2d2f9418b92a6eba7208bfcd417b302de1b70183ea2183d45a","schema_version":"1.0","event_id":"sha256:60795892fe858b2d2f9418b92a6eba7208bfcd417b302de1b70183ea2183d45a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PKJHEZS7M3GJURLMDOFZKAZYYE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+OvCphj21tDjueW68nWO8yLzU1sCasvc3/g/SDBfCFPxYrhmbFlUURlOPvij4L4/DdX5QBK24inkzwPHSFdnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:15:15.978528Z"},"content_sha256":"6aa1edb8a0635817e7e5697df5c06f7bb2555d2aba2f293ba6478833f938ee74","schema_version":"1.0","event_id":"sha256:6aa1edb8a0635817e7e5697df5c06f7bb2555d2aba2f293ba6478833f938ee74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/bundle.json","state_url":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/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":"2026-05-26T23:15:15Z","links":{"resolver":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE","bundle":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/bundle.json","state":"https://pith.science/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PKJHEZS7M3GJURLMDOFZKAZYYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PKJHEZS7M3GJURLMDOFZKAZYYE","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":"33f5869fdb754baf766777054344e2c48ebcff6514d52165666d9fd6e18d5e0e","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-07-21T09:50:36Z","title_canon_sha256":"624cc04a1d2ed95d2e675fb441535b553c44ec082dc4a0b343b78ae40d241595"},"schema_version":"1.0","source":{"id":"1707.06814","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06814","created_at":"2026-05-18T00:22:10Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06814v3","created_at":"2026-05-18T00:22:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06814","created_at":"2026-05-18T00:22:10Z"},{"alias_kind":"pith_short_12","alias_value":"PKJHEZS7M3GJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PKJHEZS7M3GJURLM","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PKJHEZS7","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:6aa1edb8a0635817e7e5697df5c06f7bb2555d2aba2f293ba6478833f938ee74","target":"graph","created_at":"2026-05-18T00:22:10Z","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":"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","authors_text":"Johan Sivertsen, Rasmus Pagh, Tobias Christiani","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-07-21T09:50:36Z","title":"Scalable and robust set similarity join"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06814","kind":"arxiv","version":3},"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":"sha256:60795892fe858b2d2f9418b92a6eba7208bfcd417b302de1b70183ea2183d45a","target":"record","created_at":"2026-05-18T00:22:10Z","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":"33f5869fdb754baf766777054344e2c48ebcff6514d52165666d9fd6e18d5e0e","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-07-21T09:50:36Z","title_canon_sha256":"624cc04a1d2ed95d2e675fb441535b553c44ec082dc4a0b343b78ae40d241595"},"schema_version":"1.0","source":{"id":"1707.06814","kind":"arxiv","version":3}},"canonical_sha256":"7a9272665f66cc9a456c1b8b950338c1248a096fc26f84ad7de43fe4d28768ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a9272665f66cc9a456c1b8b950338c1248a096fc26f84ad7de43fe4d28768ab","first_computed_at":"2026-05-18T00:22:10.842522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:10.842522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CvrtbLdz+n3VGDGLIBvR8bfunrscPTFbLTxEUmD3pFDqaHjUeNEentohdCPIYmZ8h84wAOAIZ1n/3zvkSg4CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:10.843070Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06814","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60795892fe858b2d2f9418b92a6eba7208bfcd417b302de1b70183ea2183d45a","sha256:6aa1edb8a0635817e7e5697df5c06f7bb2555d2aba2f293ba6478833f938ee74"],"state_sha256":"3eac6404011b75859be75f9dfd057e896e2ce0fed11d4529537e01ee8233bf13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T8XgJwJIFI1+LjQOJ7ARb1z9qb8dk4W75wEs5dXLKIg7HrGQsaEGn+G62UNl4x65mN8+Mp1Wvi2AKNkMlfq4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:15:15.980774Z","bundle_sha256":"6db04ac743f69c2c587a29abd9893921442115c344c1a5363e63ad23da329131"}}