{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:I47XCXC3O2FY3MDLZM7LW5YT4W","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":"1a10223925b2b5042d81f49e29df16cc7c2da37a92bf084279f45bcbe93d0c8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-06-13T21:59:11Z","title_canon_sha256":"6dede8e776dadaf3e813e7594739ee6d80e7b4379c1d2977cabc0d1a2d57ff25"},"schema_version":"1.0","source":{"id":"1706.04266","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04266","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04266v3","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04266","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"pith_short_12","alias_value":"I47XCXC3O2FY","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"I47XCXC3O2FY3MDL","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"I47XCXC3","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:9123852c9e17490ae11506400fee415d86c0b0eccd099264c758761b7144f06a","target":"graph","created_at":"2026-05-18T00:40:28Z","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":"Similarity join, which can find similar objects (e.g., products, names, addresses) across different sources, is powerful in dealing with variety in big data, especially web data. Threshold-driven similarity join, which has been extensively studied in the past, assumes that a user is able to specify a similarity threshold, and then focuses on how to efficiently return the object pairs whose similarities pass the threshold. We argue that the assumption about a well set similarity threshold may not be valid for two reasons. The optimal thresholds for different similarity join tasks may vary a lot","authors_text":"Chuancong Gao, Jiannan Wang, Jian Pei, Rui Li, Yi Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-06-13T21:59:11Z","title":"Preference-driven Similarity Join"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04266","kind":"arxiv","version":3},"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":"sha256:4a9358dab7fd3e0d7534461a3797dd86ddc7f5df593f6bf9f7bbcbede3641901","target":"record","created_at":"2026-05-18T00:40:28Z","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":"1a10223925b2b5042d81f49e29df16cc7c2da37a92bf084279f45bcbe93d0c8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-06-13T21:59:11Z","title_canon_sha256":"6dede8e776dadaf3e813e7594739ee6d80e7b4379c1d2977cabc0d1a2d57ff25"},"schema_version":"1.0","source":{"id":"1706.04266","kind":"arxiv","version":3}},"canonical_sha256":"473f715c5b768b8db06bcb3ebb7713e59d5a6bcb94a2eb65b5bf75fc707495c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"473f715c5b768b8db06bcb3ebb7713e59d5a6bcb94a2eb65b5bf75fc707495c0","first_computed_at":"2026-05-18T00:40:28.285501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:28.285501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sW4XdMlt+rO8oDypPp7TafHxnY7dbDjYmPpG1DU1nvK/A4HjcIR4WL7MKanRtAi/+dLfK0cIi5fWR2vNuUAxDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:28.286014Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04266","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a9358dab7fd3e0d7534461a3797dd86ddc7f5df593f6bf9f7bbcbede3641901","sha256:9123852c9e17490ae11506400fee415d86c0b0eccd099264c758761b7144f06a"],"state_sha256":"eba02ac703e31ee5f67371a9e32e571d3a34aa5e6a3c4e3581051e6335695c4e"}