{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:D2YQ3JVM3CIWZXP2MV2QTRY26V","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":"55299ed779028d38d25f32992960b3088e16a0d7b7a9ff4f82e31913b37935f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-02T12:45:43Z","title_canon_sha256":"1cdc03e5b7063c7e67dff167788a7fe411fbfc6eaacc1338d4612a742b02694a"},"schema_version":"1.0","source":{"id":"1507.00552","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00552","created_at":"2026-05-18T00:47:51Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00552v2","created_at":"2026-05-18T00:47:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00552","created_at":"2026-05-18T00:47:51Z"},{"alias_kind":"pith_short_12","alias_value":"D2YQ3JVM3CIW","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"D2YQ3JVM3CIWZXP2","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"D2YQ3JVM","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:1b868fd526159c82732dfec248fa2d5beb51ee4c1b896024f062af22a02e8f25","target":"graph","created_at":"2026-05-18T00:47:51Z","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 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","authors_text":"Francesco Silvestri, Morten St\\\"ockel, Ninh Pham, Rasmus Pagh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-02T12:45:43Z","title":"I/O-Efficient Similarity Join"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00552","kind":"arxiv","version":2},"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":"sha256:9140df284dae01d7814ed4c0e9a99e0a2f8c340cc7f1151975fab38f9094ca4f","target":"record","created_at":"2026-05-18T00:47:51Z","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":"55299ed779028d38d25f32992960b3088e16a0d7b7a9ff4f82e31913b37935f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-02T12:45:43Z","title_canon_sha256":"1cdc03e5b7063c7e67dff167788a7fe411fbfc6eaacc1338d4612a742b02694a"},"schema_version":"1.0","source":{"id":"1507.00552","kind":"arxiv","version":2}},"canonical_sha256":"1eb10da6acd8916cddfa657509c71af541e93dd05446342bd145f49ecee44f16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eb10da6acd8916cddfa657509c71af541e93dd05446342bd145f49ecee44f16","first_computed_at":"2026-05-18T00:47:51.312794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:51.312794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxlXxSwNWft26xrHRwy1T2aeaJM4N5tLI+6e22NApTqHC5rJZqjatYVrotQu+Beq3CAWRu+gCQL0fQhOuKg2CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:51.313478Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.00552","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9140df284dae01d7814ed4c0e9a99e0a2f8c340cc7f1151975fab38f9094ca4f","sha256:1b868fd526159c82732dfec248fa2d5beb51ee4c1b896024f062af22a02e8f25"],"state_sha256":"936e34d9e48bd8ab0416dc57a81fba76025d1d0acca7d957a0ef356de1835fe4"}