{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:JAPPLF64LSRUX7JLWSGZVFSBGD","short_pith_number":"pith:JAPPLF64","schema_version":"1.0","canonical_sha256":"481ef597dc5ca34bfd2bb48d9a964130ec45831926e0077deaa5dccb23438c47","source":{"kind":"arxiv","id":"1204.6077","version":1},"attestation_state":"computed","paper":{"title":"V-SMART-Join: A Scalable MapReduce Framework for All-Pair Similarity Joins of Multisets and Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ahmed Metwally, Christos Faloutsos","submitted_at":"2012-04-26T23:25:14Z","abstract_excerpt":"This work proposes V-SMART-Join, a scalable MapReduce-based framework for discovering all pairs of similar entities. The V-SMART-Join framework is applicable to sets, multisets, and vectors. V-SMART-Join is motivated by the observed skew in the underlying distributions of Internet traffic, and is a family of 2-stage algorithms, where the first stage computes and joins the partial results, and the second stage computes the similarity exactly for all candidate pairs. The V-SMART-Join algorithms are very efficient and scalable in the number of entities, as well as their cardinalities. They were u"},"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":"1204.6077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-04-26T23:25:14Z","cross_cats_sorted":[],"title_canon_sha256":"5b5b525f6fe60d27a53e4950ac5ddbf8afa0836e852b1c452cbea7a28c1d6f44","abstract_canon_sha256":"c0bb755b74bbbd5d0a01522fea68d35a1944e7a90221a239c6a4bf684d6d5551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:56:47.133167Z","signature_b64":"erdp0zf4IGZ84i8BqByt6e0gVIhS8HhDd3SeUgjtcR7NEaYDCCLsldaNaoMULLuTsiTBLwcLs5JwFxRjSlt0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"481ef597dc5ca34bfd2bb48d9a964130ec45831926e0077deaa5dccb23438c47","last_reissued_at":"2026-05-18T03:56:47.132529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:56:47.132529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V-SMART-Join: A Scalable MapReduce Framework for All-Pair Similarity Joins of Multisets and Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ahmed Metwally, Christos Faloutsos","submitted_at":"2012-04-26T23:25:14Z","abstract_excerpt":"This work proposes V-SMART-Join, a scalable MapReduce-based framework for discovering all pairs of similar entities. The V-SMART-Join framework is applicable to sets, multisets, and vectors. V-SMART-Join is motivated by the observed skew in the underlying distributions of Internet traffic, and is a family of 2-stage algorithms, where the first stage computes and joins the partial results, and the second stage computes the similarity exactly for all candidate pairs. The V-SMART-Join algorithms are very efficient and scalable in the number of entities, as well as their cardinalities. They were u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.6077","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":"1204.6077","created_at":"2026-05-18T03:56:47.132613+00:00"},{"alias_kind":"arxiv_version","alias_value":"1204.6077v1","created_at":"2026-05-18T03:56:47.132613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.6077","created_at":"2026-05-18T03:56:47.132613+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAPPLF64LSRU","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAPPLF64LSRUX7JL","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAPPLF64","created_at":"2026-05-18T12:27:11.947152+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/JAPPLF64LSRUX7JLWSGZVFSBGD","json":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD.json","graph_json":"https://pith.science/api/pith-number/JAPPLF64LSRUX7JLWSGZVFSBGD/graph.json","events_json":"https://pith.science/api/pith-number/JAPPLF64LSRUX7JLWSGZVFSBGD/events.json","paper":"https://pith.science/paper/JAPPLF64"},"agent_actions":{"view_html":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD","download_json":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD.json","view_paper":"https://pith.science/paper/JAPPLF64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1204.6077&json=true","fetch_graph":"https://pith.science/api/pith-number/JAPPLF64LSRUX7JLWSGZVFSBGD/graph.json","fetch_events":"https://pith.science/api/pith-number/JAPPLF64LSRUX7JLWSGZVFSBGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/action/storage_attestation","attest_author":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/action/author_attestation","sign_citation":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/action/citation_signature","submit_replication":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/action/replication_record"}},"created_at":"2026-05-18T03:56:47.132613+00:00","updated_at":"2026-05-18T03:56:47.132613+00:00"}