{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F5ZNWW2GLCOTONJLFHRYAEKLDI","short_pith_number":"pith:F5ZNWW2G","canonical_record":{"source":{"id":"2202.12521","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-02-25T06:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"462ee72a11b709be9757e515fa16d78af7cf8335e7b3f79f1af9acfc0c9827a2","abstract_canon_sha256":"f6d9a29d83b2fc21b2cb426b80ad42548605d014c7d44f1150f446c50060b63d"},"schema_version":"1.0"},"canonical_sha256":"2f72db5b46589d37352b29e380114b1a03eb4b875b9af361ac5a69caee12b482","source":{"kind":"arxiv","id":"2202.12521","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.12521","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2202.12521v5","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12521","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"F5ZNWW2GLCOT","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"F5ZNWW2GLCOTONJL","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"F5ZNWW2G","created_at":"2026-07-05T05:03:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F5ZNWW2GLCOTONJLFHRYAEKLDI","target":"record","payload":{"canonical_record":{"source":{"id":"2202.12521","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-02-25T06:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"462ee72a11b709be9757e515fa16d78af7cf8335e7b3f79f1af9acfc0c9827a2","abstract_canon_sha256":"f6d9a29d83b2fc21b2cb426b80ad42548605d014c7d44f1150f446c50060b63d"},"schema_version":"1.0"},"canonical_sha256":"2f72db5b46589d37352b29e380114b1a03eb4b875b9af361ac5a69caee12b482","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:50.400496Z","signature_b64":"zMF9zKBd/H96yKIaNADtvf/TlGZGDfGQgyB64Kb5E8WGobYWOZxgUoY8OmRnxVTAyqr5ANXWvYNFI9BBHXuaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f72db5b46589d37352b29e380114b1a03eb4b875b9af361ac5a69caee12b482","last_reissued_at":"2026-07-05T05:03:50.400081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:50.400081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.12521","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8STuebbSgUD28eas4+yvMgGJgzyGCrksjL6PqKEup1P3CeA3jND7jrzz6QwMKe9oVTXXS76Np7ZV09y8HdLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:33:50.740831Z"},"content_sha256":"03eb3e46ce420ec0483670271bfdfbd7580c4842adc9746f06fc975ab302144c","schema_version":"1.0","event_id":"sha256:03eb3e46ce420ec0483670271bfdfbd7580c4842adc9746f06fc975ab302144c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F5ZNWW2GLCOTONJLFHRYAEKLDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to reduce the search space of Entity Resolution: with Blocking or Nearest Neighbor search?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Franziska Schoger, George Mandilaras, George Papadakis, Marco Fisichella, Nikolaus Augsten, Wolfgang Nejdl","submitted_at":"2022-02-25T06:50:22Z","abstract_excerpt":"Entity Resolution suffers from quadratic time complexity. To increase its time efficiency, three kinds of filtering techniques are typically used for restricting its search space: (i) blocking workflows, which group together entity profiles with identical or similar signatures, (ii) string similarity join algorithms, which quickly detect entities more similar than a threshold, and (iii) nearest-neighbor methods, which convert every entity profile into a vector and quickly detect the closest entities according to the specified distance function. Numerous methods have been proposed for each type"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12521","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.12521/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZ+bHcQxM3cMqgoajaOX8tleLPnuE8mOzR6rriv7H7BdN4wQ7/dx3ySJJQql+nUymPM8m+WPf8Dk5Oxj4wz9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:33:50.741335Z"},"content_sha256":"98d5d869a9b82364cc2c2bb216b30fa03393d27aae0a0b049cd18f0aa2cbba11","schema_version":"1.0","event_id":"sha256:98d5d869a9b82364cc2c2bb216b30fa03393d27aae0a0b049cd18f0aa2cbba11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI/bundle.json","state_url":"https://pith.science/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI/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":"2026-08-03T21:33:50Z","links":{"resolver":"https://pith.science/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI","bundle":"https://pith.science/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI/bundle.json","state":"https://pith.science/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5ZNWW2GLCOTONJLFHRYAEKLDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F5ZNWW2GLCOTONJLFHRYAEKLDI","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":"f6d9a29d83b2fc21b2cb426b80ad42548605d014c7d44f1150f446c50060b63d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-02-25T06:50:22Z","title_canon_sha256":"462ee72a11b709be9757e515fa16d78af7cf8335e7b3f79f1af9acfc0c9827a2"},"schema_version":"1.0","source":{"id":"2202.12521","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.12521","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2202.12521v5","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12521","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"F5ZNWW2GLCOT","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"F5ZNWW2GLCOTONJL","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"F5ZNWW2G","created_at":"2026-07-05T05:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:98d5d869a9b82364cc2c2bb216b30fa03393d27aae0a0b049cd18f0aa2cbba11","target":"graph","created_at":"2026-07-05T05:03:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.12521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity Resolution suffers from quadratic time complexity. To increase its time efficiency, three kinds of filtering techniques are typically used for restricting its search space: (i) blocking workflows, which group together entity profiles with identical or similar signatures, (ii) string similarity join algorithms, which quickly detect entities more similar than a threshold, and (iii) nearest-neighbor methods, which convert every entity profile into a vector and quickly detect the closest entities according to the specified distance function. Numerous methods have been proposed for each type","authors_text":"Franziska Schoger, George Mandilaras, George Papadakis, Marco Fisichella, Nikolaus Augsten, Wolfgang Nejdl","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-02-25T06:50:22Z","title":"How to reduce the search space of Entity Resolution: with Blocking or Nearest Neighbor search?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12521","kind":"arxiv","version":5},"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":"sha256:03eb3e46ce420ec0483670271bfdfbd7580c4842adc9746f06fc975ab302144c","target":"record","created_at":"2026-07-05T05:03:50Z","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":"f6d9a29d83b2fc21b2cb426b80ad42548605d014c7d44f1150f446c50060b63d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-02-25T06:50:22Z","title_canon_sha256":"462ee72a11b709be9757e515fa16d78af7cf8335e7b3f79f1af9acfc0c9827a2"},"schema_version":"1.0","source":{"id":"2202.12521","kind":"arxiv","version":5}},"canonical_sha256":"2f72db5b46589d37352b29e380114b1a03eb4b875b9af361ac5a69caee12b482","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f72db5b46589d37352b29e380114b1a03eb4b875b9af361ac5a69caee12b482","first_computed_at":"2026-07-05T05:03:50.400081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:50.400081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMF9zKBd/H96yKIaNADtvf/TlGZGDfGQgyB64Kb5E8WGobYWOZxgUoY8OmRnxVTAyqr5ANXWvYNFI9BBHXuaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:50.400496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.12521","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03eb3e46ce420ec0483670271bfdfbd7580c4842adc9746f06fc975ab302144c","sha256:98d5d869a9b82364cc2c2bb216b30fa03393d27aae0a0b049cd18f0aa2cbba11"],"state_sha256":"b7360dee4a6032ed5b48ed610a36d77d28a45120d36e9dd27d380fde123d6a2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"POmQjNz++sm1lZDYUNjbbIYt9FZuCXFE6InPht9G0f+POvOeu0ldGEz/NYPzGkZ6aLhHmuAUeHfAOwXEHPWMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:33:50.745270Z","bundle_sha256":"3a44e82ca75e9b1ca73b03afef89d3c6ae2e687dec15d666c51031c38bffb39a"}}