{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NEQXHPT4ZP63PDTWTDVY57ISRW","short_pith_number":"pith:NEQXHPT4","schema_version":"1.0","canonical_sha256":"692173be7ccbfdb78e7698eb8efd128daa964a1b40d348c8423828599317e32e","source":{"kind":"arxiv","id":"1611.04999","version":1},"attestation_state":"computed","paper":{"title":"Massively-Parallel Similarity Join, Edge-Isoperimetry, and Distance Correlations on the Hypercube","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DC"],"primary_cat":"cs.DS","authors_text":"Cyrus Rashtchian, Paul Beame","submitted_at":"2016-11-15T19:36:28Z","abstract_excerpt":"We study distributed protocols for finding all pairs of similar vectors in a large dataset. Our results pertain to a variety of discrete metrics, and we give concrete instantiations for Hamming distance. In particular, we give improved upper bounds on the overhead required for similarity defined by Hamming distance $r>1$ and prove a lower bound showing qualitative optimality of the overhead required for similarity over any Hamming distance $r$. Our main conceptual contribution is a connection between similarity search algorithms and certain graph-theoretic quantities. For our upper bounds, we "},"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":"1611.04999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2016-11-15T19:36:28Z","cross_cats_sorted":["cs.CC","cs.DC"],"title_canon_sha256":"29abaa370654f7281f11ac4af8bc64126ea7c6963e66cc5daeb51d8b1e8e73e5","abstract_canon_sha256":"f0db37c81af9e4be39d9fe32b8670761216e524e5a714ecdd590ba53a8cb0511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:49.298162Z","signature_b64":"6bJ0jZA3YZzJPWH+U9I6PQ/cv+BmA22wbK04mPVlaRO2RBZp75D9LUY7yIlIHD/35x+itPG86ZPJwkcUCNlOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"692173be7ccbfdb78e7698eb8efd128daa964a1b40d348c8423828599317e32e","last_reissued_at":"2026-05-18T00:58:49.297580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:49.297580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively-Parallel Similarity Join, Edge-Isoperimetry, and Distance Correlations on the Hypercube","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DC"],"primary_cat":"cs.DS","authors_text":"Cyrus Rashtchian, Paul Beame","submitted_at":"2016-11-15T19:36:28Z","abstract_excerpt":"We study distributed protocols for finding all pairs of similar vectors in a large dataset. Our results pertain to a variety of discrete metrics, and we give concrete instantiations for Hamming distance. In particular, we give improved upper bounds on the overhead required for similarity defined by Hamming distance $r>1$ and prove a lower bound showing qualitative optimality of the overhead required for similarity over any Hamming distance $r$. Our main conceptual contribution is a connection between similarity search algorithms and certain graph-theoretic quantities. For our upper bounds, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04999","kind":"arxiv","version":1},"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":"1611.04999","created_at":"2026-05-18T00:58:49.297655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04999v1","created_at":"2026-05-18T00:58:49.297655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04999","created_at":"2026-05-18T00:58:49.297655+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEQXHPT4ZP63","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEQXHPT4ZP63PDTW","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEQXHPT4","created_at":"2026-05-18T12:30:32.724797+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/NEQXHPT4ZP63PDTWTDVY57ISRW","json":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW.json","graph_json":"https://pith.science/api/pith-number/NEQXHPT4ZP63PDTWTDVY57ISRW/graph.json","events_json":"https://pith.science/api/pith-number/NEQXHPT4ZP63PDTWTDVY57ISRW/events.json","paper":"https://pith.science/paper/NEQXHPT4"},"agent_actions":{"view_html":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW","download_json":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW.json","view_paper":"https://pith.science/paper/NEQXHPT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04999&json=true","fetch_graph":"https://pith.science/api/pith-number/NEQXHPT4ZP63PDTWTDVY57ISRW/graph.json","fetch_events":"https://pith.science/api/pith-number/NEQXHPT4ZP63PDTWTDVY57ISRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW/action/storage_attestation","attest_author":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW/action/author_attestation","sign_citation":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW/action/citation_signature","submit_replication":"https://pith.science/pith/NEQXHPT4ZP63PDTWTDVY57ISRW/action/replication_record"}},"created_at":"2026-05-18T00:58:49.297655+00:00","updated_at":"2026-05-18T00:58:49.297655+00:00"}