{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N4P4QQ4L326W3RCVZIXEIXJ4YE","short_pith_number":"pith:N4P4QQ4L","schema_version":"1.0","canonical_sha256":"6f1fc8438bdebd6dc455ca2e445d3cc125d2b439d8ce3eaca4b42b60a701f3a3","source":{"kind":"arxiv","id":"1807.10727","version":1},"attestation_state":"computed","paper":{"title":"Connected Components at Scale via Local Contractions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DC","authors_text":"Jakub {\\L}\\k{a}cki, Micha{\\l} W{\\l}odarczyk, Vahab Mirrokni","submitted_at":"2018-07-27T16:53:45Z","abstract_excerpt":"As a fundamental tool in hierarchical graph clustering, computing connected components has been a central problem in large-scale data mining. While many known algorithms have been developed for this problem, they are either not scalable in practice or lack strong theoretical guarantees on the parallel running time, that is, the number of communication rounds. So far, the best proven guarantee is $\\Oh(\\log n)$, which matches the running time in the PRAM model.\n  In this paper, we aim to design a distributed algorithm for this problem that works well in theory and practice. In particular, we pre"},"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":"1807.10727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-07-27T16:53:45Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"96935afdc729a00375d52b8f9c81112b12ee898979511ec552768e40d1e652e3","abstract_canon_sha256":"d3d7bacd2e2ba32dbdef81218255a904c5478bb3325f222f570f908fdbc10329"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:39.703456Z","signature_b64":"6o71rSCWywKtwOJH33+YVvvZYUH57kcL9N3/0UtsvPAW1QdfpAO9KMxCR90l66OyIBN8UjF3W/epziBPdT5xAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f1fc8438bdebd6dc455ca2e445d3cc125d2b439d8ce3eaca4b42b60a701f3a3","last_reissued_at":"2026-05-18T00:09:39.702816Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:39.702816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Connected Components at Scale via Local Contractions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DC","authors_text":"Jakub {\\L}\\k{a}cki, Micha{\\l} W{\\l}odarczyk, Vahab Mirrokni","submitted_at":"2018-07-27T16:53:45Z","abstract_excerpt":"As a fundamental tool in hierarchical graph clustering, computing connected components has been a central problem in large-scale data mining. While many known algorithms have been developed for this problem, they are either not scalable in practice or lack strong theoretical guarantees on the parallel running time, that is, the number of communication rounds. So far, the best proven guarantee is $\\Oh(\\log n)$, which matches the running time in the PRAM model.\n  In this paper, we aim to design a distributed algorithm for this problem that works well in theory and practice. In particular, we pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10727","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":"1807.10727","created_at":"2026-05-18T00:09:39.702914+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10727v1","created_at":"2026-05-18T00:09:39.702914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10727","created_at":"2026-05-18T00:09:39.702914+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4P4QQ4L326W","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4P4QQ4L326W3RCV","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4P4QQ4L","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2107.06499","citing_title":"Deduplicating Training Data Makes Language Models Better","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE","json":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE.json","graph_json":"https://pith.science/api/pith-number/N4P4QQ4L326W3RCVZIXEIXJ4YE/graph.json","events_json":"https://pith.science/api/pith-number/N4P4QQ4L326W3RCVZIXEIXJ4YE/events.json","paper":"https://pith.science/paper/N4P4QQ4L"},"agent_actions":{"view_html":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE","download_json":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE.json","view_paper":"https://pith.science/paper/N4P4QQ4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10727&json=true","fetch_graph":"https://pith.science/api/pith-number/N4P4QQ4L326W3RCVZIXEIXJ4YE/graph.json","fetch_events":"https://pith.science/api/pith-number/N4P4QQ4L326W3RCVZIXEIXJ4YE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE/action/storage_attestation","attest_author":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE/action/author_attestation","sign_citation":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE/action/citation_signature","submit_replication":"https://pith.science/pith/N4P4QQ4L326W3RCVZIXEIXJ4YE/action/replication_record"}},"created_at":"2026-05-18T00:09:39.702914+00:00","updated_at":"2026-05-18T00:09:39.702914+00:00"}