{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:H22J2BSHV7QOTMT7O2RFE3C3G4","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":"b5d93d7b1a5fcd931d3603c55c4a644a691d460866f8a4c3a11f233d39f8d87a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2010-10-15T00:28:44Z","title_canon_sha256":"8532e64adf204580f09a63689f5ec42b8ccdc2aa1e78862612feaa437908d978"},"schema_version":"1.0","source":{"id":"1010.3053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1010.3053","created_at":"2026-05-18T04:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"1010.3053v1","created_at":"2026-05-18T04:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1010.3053","created_at":"2026-05-18T04:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"H22J2BSHV7QO","created_at":"2026-05-18T12:26:07Z"},{"alias_kind":"pith_short_16","alias_value":"H22J2BSHV7QOTMT7","created_at":"2026-05-18T12:26:07Z"},{"alias_kind":"pith_short_8","alias_value":"H22J2BSH","created_at":"2026-05-18T12:26:07Z"}],"graph_snapshots":[{"event_id":"sha256:109ce7ccbfe3ca829a954cbe2c4a682d70cf7dfa70c3c9e40f8049be53dcda11","target":"graph","created_at":"2026-05-18T04:39:17Z","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":"Cloud infrastructures enable the efficient parallel execution of data-intensive tasks such as entity resolution on large datasets. We investigate challenges and possible solutions of using the MapReduce programming model for parallel entity resolution. In particular, we propose and evaluate two MapReduce-based implementations for Sorted Neighborhood blocking that either use multiple MapReduce jobs or apply a tailored data replication.","authors_text":"Andreas Thor, Erhard Rahm, Lars Kolb","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2010-10-15T00:28:44Z","title":"Parallel Sorted Neighborhood Blocking with MapReduce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1010.3053","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":"sha256:2d278f85ba502424c59a86e56861c0e3d636fe0fa392919249e80ab84d7aeff8","target":"record","created_at":"2026-05-18T04:39:17Z","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":"b5d93d7b1a5fcd931d3603c55c4a644a691d460866f8a4c3a11f233d39f8d87a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2010-10-15T00:28:44Z","title_canon_sha256":"8532e64adf204580f09a63689f5ec42b8ccdc2aa1e78862612feaa437908d978"},"schema_version":"1.0","source":{"id":"1010.3053","kind":"arxiv","version":1}},"canonical_sha256":"3eb49d0647afe0e9b27f76a2526c5b37067426e47d9baaedc89d30f52a305729","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eb49d0647afe0e9b27f76a2526c5b37067426e47d9baaedc89d30f52a305729","first_computed_at":"2026-05-18T04:39:17.932166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:39:17.932166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L17HLgoCiVlt699Na69NLFtvrbAtsMiZtWoZA+9C0uY5tPPDQGnZxnLCBWhuS+i2/loMT05U+1REQeHg5RTBCg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:39:17.932897Z","signed_message":"canonical_sha256_bytes"},"source_id":"1010.3053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d278f85ba502424c59a86e56861c0e3d636fe0fa392919249e80ab84d7aeff8","sha256:109ce7ccbfe3ca829a954cbe2c4a682d70cf7dfa70c3c9e40f8049be53dcda11"],"state_sha256":"b116f6b1106b4154fdcaa352bc35c344ea95c494e601ff74e5dc5edaf6307444"}