{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:DMPRG4YNCIHZFY4AJRRWJFYRBM","short_pith_number":"pith:DMPRG4YN","canonical_record":{"source":{"id":"1407.3191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-07-11T15:06:03Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"72f2411a22f16daf5df85c8a292618c2c64e6b5753ec0a43c582fe69f9b13d7f","abstract_canon_sha256":"80a0ba165f708bf4ebb2e1265eb9a2f8bf0ee1571c110220a9370f5ab755f818"},"schema_version":"1.0"},"canonical_sha256":"1b1f13730d120f92e3804c636497110b3c7bcfae1814f3db1000e6cdbe5d7132","source":{"kind":"arxiv","id":"1407.3191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.3191","created_at":"2026-05-18T02:47:51Z"},{"alias_kind":"arxiv_version","alias_value":"1407.3191v1","created_at":"2026-05-18T02:47:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.3191","created_at":"2026-05-18T02:47:51Z"},{"alias_kind":"pith_short_12","alias_value":"DMPRG4YNCIHZ","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DMPRG4YNCIHZFY4A","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DMPRG4YN","created_at":"2026-05-18T12:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:DMPRG4YNCIHZFY4AJRRWJFYRBM","target":"record","payload":{"canonical_record":{"source":{"id":"1407.3191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-07-11T15:06:03Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"72f2411a22f16daf5df85c8a292618c2c64e6b5753ec0a43c582fe69f9b13d7f","abstract_canon_sha256":"80a0ba165f708bf4ebb2e1265eb9a2f8bf0ee1571c110220a9370f5ab755f818"},"schema_version":"1.0"},"canonical_sha256":"1b1f13730d120f92e3804c636497110b3c7bcfae1814f3db1000e6cdbe5d7132","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:47:51.791948Z","signature_b64":"Liu1JVI8gEMYboz+09C6H8egnrgNe3wtQDtnYk11bL6lYocKTzIoXKd/VBrHkEr8DYv0HOMFON8Z4Ru3gLNODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b1f13730d120f92e3804c636497110b3c7bcfae1814f3db1000e6cdbe5d7132","last_reissued_at":"2026-05-18T02:47:51.791506Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:47:51.791506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1407.3191","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":"2026-05-18T02:47:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aNPxeBDKKvcFaFf0cLWPDPBk51sLxNugAYnmzOw9AOuDdY1ZuC/XHe4ZZ6Qwp61jgPqqHaKQzxc1FoSGtiWJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:14:26.124955Z"},"content_sha256":"d71038f4d6247831c95bb9ad1af90639183bcf651f6d3b07b5b7fcdc26cc233b","schema_version":"1.0","event_id":"sha256:d71038f4d6247831c95bb9ad1af90639183bcf651f6d3b07b5b7fcdc26cc233b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:DMPRG4YNCIHZFY4AJRRWJFYRBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison of Blocking Methods for Record Linkage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.DB","authors_text":"Mauricio Sadinle, Rebecca C. Steorts, Samuel L. Ventura, Stephen E. Fienberg","submitted_at":"2014-07-11T15:06:03Z","abstract_excerpt":"Record linkage seeks to merge databases and to remove duplicates when unique identifiers are not available. Most approaches use blocking techniques to reduce the computational complexity associated with record linkage. We review traditional blocking techniques, which typically partition the records according to a set of field attributes, and consider two variants of a method known as locality sensitive hashing, sometimes referred to as \"private blocking.\" We compare these approaches in terms of their recall, reduction ratio, and computational complexity. We evaluate these methods using differe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.3191","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":"2026-05-18T02:47:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q3aeT2L3vkcR5cqpbPDfS1V0yrv4ZIHieMpqSmmen+C/bh2Ch42Kj4/KgqhxzHAgInXqOcokJoc1KXcTfWa4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:14:26.125651Z"},"content_sha256":"b843d524905a6bc0f2c2985342b42bfa4bac7aea1695dc897397d36b2754ce94","schema_version":"1.0","event_id":"sha256:b843d524905a6bc0f2c2985342b42bfa4bac7aea1695dc897397d36b2754ce94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM/bundle.json","state_url":"https://pith.science/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM/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":"2026-05-28T23:14:26Z","links":{"resolver":"https://pith.science/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM","bundle":"https://pith.science/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM/bundle.json","state":"https://pith.science/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMPRG4YNCIHZFY4AJRRWJFYRBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DMPRG4YNCIHZFY4AJRRWJFYRBM","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":"80a0ba165f708bf4ebb2e1265eb9a2f8bf0ee1571c110220a9370f5ab755f818","cross_cats_sorted":["stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-07-11T15:06:03Z","title_canon_sha256":"72f2411a22f16daf5df85c8a292618c2c64e6b5753ec0a43c582fe69f9b13d7f"},"schema_version":"1.0","source":{"id":"1407.3191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.3191","created_at":"2026-05-18T02:47:51Z"},{"alias_kind":"arxiv_version","alias_value":"1407.3191v1","created_at":"2026-05-18T02:47:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.3191","created_at":"2026-05-18T02:47:51Z"},{"alias_kind":"pith_short_12","alias_value":"DMPRG4YNCIHZ","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DMPRG4YNCIHZFY4A","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DMPRG4YN","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:b843d524905a6bc0f2c2985342b42bfa4bac7aea1695dc897397d36b2754ce94","target":"graph","created_at":"2026-05-18T02:47:51Z","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":"Record linkage seeks to merge databases and to remove duplicates when unique identifiers are not available. Most approaches use blocking techniques to reduce the computational complexity associated with record linkage. We review traditional blocking techniques, which typically partition the records according to a set of field attributes, and consider two variants of a method known as locality sensitive hashing, sometimes referred to as \"private blocking.\" We compare these approaches in terms of their recall, reduction ratio, and computational complexity. We evaluate these methods using differe","authors_text":"Mauricio Sadinle, Rebecca C. Steorts, Samuel L. Ventura, Stephen E. Fienberg","cross_cats":["stat.AP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-07-11T15:06:03Z","title":"A Comparison of Blocking Methods for Record Linkage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.3191","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:d71038f4d6247831c95bb9ad1af90639183bcf651f6d3b07b5b7fcdc26cc233b","target":"record","created_at":"2026-05-18T02:47:51Z","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":"80a0ba165f708bf4ebb2e1265eb9a2f8bf0ee1571c110220a9370f5ab755f818","cross_cats_sorted":["stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-07-11T15:06:03Z","title_canon_sha256":"72f2411a22f16daf5df85c8a292618c2c64e6b5753ec0a43c582fe69f9b13d7f"},"schema_version":"1.0","source":{"id":"1407.3191","kind":"arxiv","version":1}},"canonical_sha256":"1b1f13730d120f92e3804c636497110b3c7bcfae1814f3db1000e6cdbe5d7132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b1f13730d120f92e3804c636497110b3c7bcfae1814f3db1000e6cdbe5d7132","first_computed_at":"2026-05-18T02:47:51.791506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:47:51.791506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Liu1JVI8gEMYboz+09C6H8egnrgNe3wtQDtnYk11bL6lYocKTzIoXKd/VBrHkEr8DYv0HOMFON8Z4Ru3gLNODw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:47:51.791948Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.3191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d71038f4d6247831c95bb9ad1af90639183bcf651f6d3b07b5b7fcdc26cc233b","sha256:b843d524905a6bc0f2c2985342b42bfa4bac7aea1695dc897397d36b2754ce94"],"state_sha256":"a32da630f8f3cf46f1fddfa9dfa6cf67455d31cafb2e9a2957b2c05b5def4963"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOMZVcLJp133DWaa8q8oYof5V6M97JYejzxXVIMHoKc7WYo5u+Wi6X5oZGjHgOXzZAM7UmxaZFUPeONpL8KqCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:14:26.129367Z","bundle_sha256":"cfb5d6c6f2d3181a714cdacad6ad0265f285ddc0d64be7f5665b8f23a054d46d"}}