{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:BQO52E2LOOX4ALQBLKHS4SMS6W","short_pith_number":"pith:BQO52E2L","schema_version":"1.0","canonical_sha256":"0c1ddd134b73afc02e015a8f2e4992f580809df0a0d9d62012d7c478666c1fb2","source":{"kind":"arxiv","id":"1108.1631","version":1},"attestation_state":"computed","paper":{"title":"Load Balancing for MapReduce-based Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Andreas Thor, Erhard Rahm, Lars Kolb","submitted_at":"2011-08-08T08:48:57Z","abstract_excerpt":"The effectiveness and scalability of MapReduce-based implementations of complex data-intensive tasks depend on an even redistribution of data between map and reduce tasks. In the presence of skewed data, sophisticated redistribution approaches thus become necessary to achieve load balancing among all reduce tasks to be executed in parallel. For the complex problem of entity resolution, we propose and evaluate two approaches for such skew handling and load balancing. The approaches support blocking techniques to reduce the search space of entity resolution, utilize a preprocessing MapReduce job"},"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":"1108.1631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2011-08-08T08:48:57Z","cross_cats_sorted":[],"title_canon_sha256":"01f85742a03dfd1bf9353aede2feb94fa0b7a356fafc4fbbc61b514741d7ea12","abstract_canon_sha256":"71c01b57167853c336919da03d8a793f27ea16339545f46833d2f9d36c4243f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:42.387766Z","signature_b64":"IR2UXzxhCLLPI/qGqTehIqkVqqgPW1mUTdoCylo49UQ/hs7uJo3NQEXQ7DC/6C6bKC6e4rqikN7mdrf2HMlqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1ddd134b73afc02e015a8f2e4992f580809df0a0d9d62012d7c478666c1fb2","last_reissued_at":"2026-05-18T02:21:42.387388Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:42.387388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Load Balancing for MapReduce-based Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Andreas Thor, Erhard Rahm, Lars Kolb","submitted_at":"2011-08-08T08:48:57Z","abstract_excerpt":"The effectiveness and scalability of MapReduce-based implementations of complex data-intensive tasks depend on an even redistribution of data between map and reduce tasks. In the presence of skewed data, sophisticated redistribution approaches thus become necessary to achieve load balancing among all reduce tasks to be executed in parallel. For the complex problem of entity resolution, we propose and evaluate two approaches for such skew handling and load balancing. The approaches support blocking techniques to reduce the search space of entity resolution, utilize a preprocessing MapReduce job"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.1631","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":"1108.1631","created_at":"2026-05-18T02:21:42.387451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1108.1631v1","created_at":"2026-05-18T02:21:42.387451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.1631","created_at":"2026-05-18T02:21:42.387451+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQO52E2LOOX4","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQO52E2LOOX4ALQB","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQO52E2L","created_at":"2026-05-18T12:26:24.575870+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/BQO52E2LOOX4ALQBLKHS4SMS6W","json":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W.json","graph_json":"https://pith.science/api/pith-number/BQO52E2LOOX4ALQBLKHS4SMS6W/graph.json","events_json":"https://pith.science/api/pith-number/BQO52E2LOOX4ALQBLKHS4SMS6W/events.json","paper":"https://pith.science/paper/BQO52E2L"},"agent_actions":{"view_html":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W","download_json":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W.json","view_paper":"https://pith.science/paper/BQO52E2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1108.1631&json=true","fetch_graph":"https://pith.science/api/pith-number/BQO52E2LOOX4ALQBLKHS4SMS6W/graph.json","fetch_events":"https://pith.science/api/pith-number/BQO52E2LOOX4ALQBLKHS4SMS6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W/action/storage_attestation","attest_author":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W/action/author_attestation","sign_citation":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W/action/citation_signature","submit_replication":"https://pith.science/pith/BQO52E2LOOX4ALQBLKHS4SMS6W/action/replication_record"}},"created_at":"2026-05-18T02:21:42.387451+00:00","updated_at":"2026-05-18T02:21:42.387451+00:00"}