{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZLOG56AIBQEDG2P72M5RECF3TL","short_pith_number":"pith:ZLOG56AI","canonical_record":{"source":{"id":"1810.05497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-11T01:16:31Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"title_canon_sha256":"ce56ee20274b4a2e5ef9177e21968db1fc201abbdebb47d6aac35760ae9fa563","abstract_canon_sha256":"2426daa1c6b1f8319f96b45e1184306166c1651a078ee713ab55d244cc60d6eb"},"schema_version":"1.0"},"canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","source":{"kind":"arxiv","id":"1810.05497","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05497","created_at":"2026-05-18T00:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05497v1","created_at":"2026-05-18T00:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05497","created_at":"2026-05-18T00:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZLOG56AIBQED","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZLOG56AIBQEDG2P7","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZLOG56AI","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZLOG56AIBQEDG2P72M5RECF3TL","target":"record","payload":{"canonical_record":{"source":{"id":"1810.05497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-11T01:16:31Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"title_canon_sha256":"ce56ee20274b4a2e5ef9177e21968db1fc201abbdebb47d6aac35760ae9fa563","abstract_canon_sha256":"2426daa1c6b1f8319f96b45e1184306166c1651a078ee713ab55d244cc60d6eb"},"schema_version":"1.0"},"canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:30.319611Z","signature_b64":"QOwGie992bYR1ItpdE095bFVt4CpToYs2JnoaWn3Lim4ffN+T0XH6SssdIW3KD/XHZyMIrAXETvr1qoMrJyFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","last_reissued_at":"2026-05-18T00:03:30.318999Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:30.318999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.05497","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":"2026-05-18T00:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLLxNbPc5mTq0anBKaaUF/QeV7bcLCYbE02qkXKrocKNWCkYHcUIgg7AfU2anhFwYX8nmzSiNAFcj0zfB5yADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T13:43:31.612331Z"},"content_sha256":"aa1b80a651eae725bf4d64fd35c0926f83f3d359292b5e52fcc914bc35c2bb9a","schema_version":"1.0","event_id":"sha256:aa1b80a651eae725bf4d64fd35c0926f83f3d359292b5e52fcc914bc35c2bb9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZLOG56AIBQEDG2P72M5RECF3TL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Blocking with An Application to the Syrian Conflict","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ML"],"primary_cat":"cs.DB","authors_text":"Anshumali Shrivastava, Rebecca C. Steorts","submitted_at":"2018-10-11T01:16:31Z","abstract_excerpt":"Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce $k$-means locality sensitive hashing (KLSH), which is based upon the information retrieval literature and clusters similar records into blocks using a vector-space representation and projections. Second, we introduce a subquadratic variant of LSH to the literature, known as Densified One Permutation Hashing (DOPH). Third, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05497","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":"2026-05-18T00:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANmdPpxcvJjtKBu5YBSDVzQvIfZyhkZrxuSt/iACMm+CCkzyIona4SfYz3j6vhGaLgAaglzDRJA8GzSo+Cf9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T13:43:31.612685Z"},"content_sha256":"2736c4fc13e11e6a056b4fccd8ae930f6088cb708cbfafac976375882a1ddac1","schema_version":"1.0","event_id":"sha256:2736c4fc13e11e6a056b4fccd8ae930f6088cb708cbfafac976375882a1ddac1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/bundle.json","state_url":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLOG56AIBQEDG2P72M5RECF3TL/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":"2026-06-21T13:43:31Z","links":{"resolver":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL","bundle":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/bundle.json","state":"https://pith.science/pith/ZLOG56AIBQEDG2P72M5RECF3TL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLOG56AIBQEDG2P72M5RECF3TL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZLOG56AIBQEDG2P72M5RECF3TL","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":"2426daa1c6b1f8319f96b45e1184306166c1651a078ee713ab55d244cc60d6eb","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-11T01:16:31Z","title_canon_sha256":"ce56ee20274b4a2e5ef9177e21968db1fc201abbdebb47d6aac35760ae9fa563"},"schema_version":"1.0","source":{"id":"1810.05497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05497","created_at":"2026-05-18T00:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05497v1","created_at":"2026-05-18T00:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05497","created_at":"2026-05-18T00:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZLOG56AIBQED","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZLOG56AIBQEDG2P7","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZLOG56AI","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:2736c4fc13e11e6a056b4fccd8ae930f6088cb708cbfafac976375882a1ddac1","target":"graph","created_at":"2026-05-18T00:03:30Z","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":"Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce $k$-means locality sensitive hashing (KLSH), which is based upon the information retrieval literature and clusters similar records into blocks using a vector-space representation and projections. Second, we introduce a subquadratic variant of LSH to the literature, known as Densified One Permutation Hashing (DOPH). Third, we propose ","authors_text":"Anshumali Shrivastava, Rebecca C. Steorts","cross_cats":["cs.LG","stat.AP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-11T01:16:31Z","title":"Probabilistic Blocking with An Application to the Syrian Conflict"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05497","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:aa1b80a651eae725bf4d64fd35c0926f83f3d359292b5e52fcc914bc35c2bb9a","target":"record","created_at":"2026-05-18T00:03:30Z","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":"2426daa1c6b1f8319f96b45e1184306166c1651a078ee713ab55d244cc60d6eb","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-11T01:16:31Z","title_canon_sha256":"ce56ee20274b4a2e5ef9177e21968db1fc201abbdebb47d6aac35760ae9fa563"},"schema_version":"1.0","source":{"id":"1810.05497","kind":"arxiv","version":1}},"canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cadc6ef8080c083369ffd33b1208bb9ae3cd410a8e3d75aa54ec4b3f9543e36e","first_computed_at":"2026-05-18T00:03:30.318999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:30.318999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QOwGie992bYR1ItpdE095bFVt4CpToYs2JnoaWn3Lim4ffN+T0XH6SssdIW3KD/XHZyMIrAXETvr1qoMrJyFBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:30.319611Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.05497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa1b80a651eae725bf4d64fd35c0926f83f3d359292b5e52fcc914bc35c2bb9a","sha256:2736c4fc13e11e6a056b4fccd8ae930f6088cb708cbfafac976375882a1ddac1"],"state_sha256":"07fe589de12c0ac9fce337f808019b806fa0c8f2ee9ca84cd23fe301fc78b242"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCA124n7M7DRsV4k1CcbVnlSttkTX298b+qxRyUuPA/IqPjzkEldwBRJf2/C2roI4gZ+B7gYQGV6H/GsXOPoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-21T13:43:31.614662Z","bundle_sha256":"8ffcaabbf0963978ba6367033562863894bb02e96c5e61dd680abd278fb8fecf"}}