{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:JAPPLF64LSRUX7JLWSGZVFSBGD","short_pith_number":"pith:JAPPLF64","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"},"canonical_sha256":"481ef597dc5ca34bfd2bb48d9a964130ec45831926e0077deaa5dccb23438c47","source":{"kind":"arxiv","id":"1204.6077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1204.6077","created_at":"2026-05-18T03:56:47Z"},{"alias_kind":"arxiv_version","alias_value":"1204.6077v1","created_at":"2026-05-18T03:56:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.6077","created_at":"2026-05-18T03:56:47Z"},{"alias_kind":"pith_short_12","alias_value":"JAPPLF64LSRU","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"JAPPLF64LSRUX7JL","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"JAPPLF64","created_at":"2026-05-18T12:27:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:JAPPLF64LSRUX7JLWSGZVFSBGD","target":"record","payload":{"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"},"canonical_sha256":"481ef597dc5ca34bfd2bb48d9a964130ec45831926e0077deaa5dccb23438c47","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"},"source_kind":"arxiv","source_id":"1204.6077","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:56:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h4KQ2Ltqz/5Imnf12+K83e4nTi0JQorTAjU+m9pAAiSeIvHmJ8KswchqRI5ILi9S9F1tvfYBMOwPlCELVVQ1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:34:25.173537Z"},"content_sha256":"d1eb1628406c2763af7d9123bca803ea1b781626f13e421ae241ede5c11c97dd","schema_version":"1.0","event_id":"sha256:d1eb1628406c2763af7d9123bca803ea1b781626f13e421ae241ede5c11c97dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:JAPPLF64LSRUX7JLWSGZVFSBGD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:56:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"twd7PTVUMFvYdZTetbLrAoc4fUMguV0YSekVFvAEZHdMmSFIBUy9NO9HSLyjMIP3E9N85CTZF1lREoIo7b+dAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:34:25.173895Z"},"content_sha256":"8d348910101159ffb948801e9dfa449273705e5c68e1061fde3c05a4931a70dc","schema_version":"1.0","event_id":"sha256:8d348910101159ffb948801e9dfa449273705e5c68e1061fde3c05a4931a70dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/bundle.json","state_url":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/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":"2026-05-30T08:34:25Z","links":{"resolver":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD","bundle":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/bundle.json","state":"https://pith.science/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAPPLF64LSRUX7JLWSGZVFSBGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:JAPPLF64LSRUX7JLWSGZVFSBGD","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":"c0bb755b74bbbd5d0a01522fea68d35a1944e7a90221a239c6a4bf684d6d5551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-04-26T23:25:14Z","title_canon_sha256":"5b5b525f6fe60d27a53e4950ac5ddbf8afa0836e852b1c452cbea7a28c1d6f44"},"schema_version":"1.0","source":{"id":"1204.6077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1204.6077","created_at":"2026-05-18T03:56:47Z"},{"alias_kind":"arxiv_version","alias_value":"1204.6077v1","created_at":"2026-05-18T03:56:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.6077","created_at":"2026-05-18T03:56:47Z"},{"alias_kind":"pith_short_12","alias_value":"JAPPLF64LSRU","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"JAPPLF64LSRUX7JL","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"JAPPLF64","created_at":"2026-05-18T12:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:8d348910101159ffb948801e9dfa449273705e5c68e1061fde3c05a4931a70dc","target":"graph","created_at":"2026-05-18T03:56:47Z","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":"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","authors_text":"Ahmed Metwally, Christos Faloutsos","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-04-26T23:25:14Z","title":"V-SMART-Join: A Scalable MapReduce Framework for All-Pair Similarity Joins of Multisets and Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.6077","kind":"arxiv","version":1},"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:d1eb1628406c2763af7d9123bca803ea1b781626f13e421ae241ede5c11c97dd","target":"record","created_at":"2026-05-18T03:56:47Z","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":"c0bb755b74bbbd5d0a01522fea68d35a1944e7a90221a239c6a4bf684d6d5551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-04-26T23:25:14Z","title_canon_sha256":"5b5b525f6fe60d27a53e4950ac5ddbf8afa0836e852b1c452cbea7a28c1d6f44"},"schema_version":"1.0","source":{"id":"1204.6077","kind":"arxiv","version":1}},"canonical_sha256":"481ef597dc5ca34bfd2bb48d9a964130ec45831926e0077deaa5dccb23438c47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"481ef597dc5ca34bfd2bb48d9a964130ec45831926e0077deaa5dccb23438c47","first_computed_at":"2026-05-18T03:56:47.132529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:56:47.132529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erdp0zf4IGZ84i8BqByt6e0gVIhS8HhDd3SeUgjtcR7NEaYDCCLsldaNaoMULLuTsiTBLwcLs5JwFxRjSlt0Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:56:47.133167Z","signed_message":"canonical_sha256_bytes"},"source_id":"1204.6077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1eb1628406c2763af7d9123bca803ea1b781626f13e421ae241ede5c11c97dd","sha256:8d348910101159ffb948801e9dfa449273705e5c68e1061fde3c05a4931a70dc"],"state_sha256":"509bb7d88ecae9d92083f4d9c05a17437efa956e3fc15bf728368a4f2473d5f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+59vpoBYpLmnYdivV4mQjFu4AXHzVTJ6ugiiRaH0XZisaqa/s010jsQWgdbvYY5GVLZmLlzh32lsxSnUirJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:34:25.175936Z","bundle_sha256":"5428a75fe644454777832b5e842bc5ce7fadaa5f7d1701bdd1009adfb222675a"}}