{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:D2YQ3JVM3CIWZXP2MV2QTRY26V","short_pith_number":"pith:D2YQ3JVM","schema_version":"1.0","canonical_sha256":"1eb10da6acd8916cddfa657509c71af541e93dd05446342bd145f49ecee44f16","source":{"kind":"arxiv","id":"1507.00552","version":2},"attestation_state":"computed","paper":{"title":"I/O-Efficient Similarity Join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Francesco Silvestri, Morten St\\\"ockel, Ninh Pham, Rasmus Pagh","submitted_at":"2015-07-02T12:45:43Z","abstract_excerpt":"We present an I/O-efficient algorithm for computing similarity joins based on locality-sensitive hashing (LSH). In contrast to the filtering methods commonly suggested our method has provable sub-quadratic dependency on the data size. Further, in contrast to straightforward implementations of known LSH-based algorithms on external memory, our approach is able to take significant advantage of the available internal memory: Whereas the time complexity of classical algorithms includes a factor of $N^\\rho$, where $\\rho$ is a parameter of the LSH used, the I/O complexity of our algorithm merely inc"},"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":"1507.00552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-02T12:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"1cdc03e5b7063c7e67dff167788a7fe411fbfc6eaacc1338d4612a742b02694a","abstract_canon_sha256":"55299ed779028d38d25f32992960b3088e16a0d7b7a9ff4f82e31913b37935f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:51.313478Z","signature_b64":"hxlXxSwNWft26xrHRwy1T2aeaJM4N5tLI+6e22NApTqHC5rJZqjatYVrotQu+Beq3CAWRu+gCQL0fQhOuKg2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eb10da6acd8916cddfa657509c71af541e93dd05446342bd145f49ecee44f16","last_reissued_at":"2026-05-18T00:47:51.312794Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:51.312794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I/O-Efficient Similarity Join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Francesco Silvestri, Morten St\\\"ockel, Ninh Pham, Rasmus Pagh","submitted_at":"2015-07-02T12:45:43Z","abstract_excerpt":"We present an I/O-efficient algorithm for computing similarity joins based on locality-sensitive hashing (LSH). In contrast to the filtering methods commonly suggested our method has provable sub-quadratic dependency on the data size. Further, in contrast to straightforward implementations of known LSH-based algorithms on external memory, our approach is able to take significant advantage of the available internal memory: Whereas the time complexity of classical algorithms includes a factor of $N^\\rho$, where $\\rho$ is a parameter of the LSH used, the I/O complexity of our algorithm merely inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00552","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":"1507.00552","created_at":"2026-05-18T00:47:51.312897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.00552v2","created_at":"2026-05-18T00:47:51.312897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00552","created_at":"2026-05-18T00:47:51.312897+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2YQ3JVM3CIW","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2YQ3JVM3CIWZXP2","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2YQ3JVM","created_at":"2026-05-18T12:29:17.054201+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/D2YQ3JVM3CIWZXP2MV2QTRY26V","json":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V.json","graph_json":"https://pith.science/api/pith-number/D2YQ3JVM3CIWZXP2MV2QTRY26V/graph.json","events_json":"https://pith.science/api/pith-number/D2YQ3JVM3CIWZXP2MV2QTRY26V/events.json","paper":"https://pith.science/paper/D2YQ3JVM"},"agent_actions":{"view_html":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V","download_json":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V.json","view_paper":"https://pith.science/paper/D2YQ3JVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.00552&json=true","fetch_graph":"https://pith.science/api/pith-number/D2YQ3JVM3CIWZXP2MV2QTRY26V/graph.json","fetch_events":"https://pith.science/api/pith-number/D2YQ3JVM3CIWZXP2MV2QTRY26V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V/action/storage_attestation","attest_author":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V/action/author_attestation","sign_citation":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V/action/citation_signature","submit_replication":"https://pith.science/pith/D2YQ3JVM3CIWZXP2MV2QTRY26V/action/replication_record"}},"created_at":"2026-05-18T00:47:51.312897+00:00","updated_at":"2026-05-18T00:47:51.312897+00:00"}