{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:I47XCXC3O2FY3MDLZM7LW5YT4W","short_pith_number":"pith:I47XCXC3","schema_version":"1.0","canonical_sha256":"473f715c5b768b8db06bcb3ebb7713e59d5a6bcb94a2eb65b5bf75fc707495c0","source":{"kind":"arxiv","id":"1706.04266","version":3},"attestation_state":"computed","paper":{"title":"Preference-driven Similarity Join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chuancong Gao, Jiannan Wang, Jian Pei, Rui Li, Yi Chang","submitted_at":"2017-06-13T21:59:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1706.04266","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-06-13T21:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"6dede8e776dadaf3e813e7594739ee6d80e7b4379c1d2977cabc0d1a2d57ff25","abstract_canon_sha256":"1a10223925b2b5042d81f49e29df16cc7c2da37a92bf084279f45bcbe93d0c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:28.286014Z","signature_b64":"sW4XdMlt+rO8oDypPp7TafHxnY7dbDjYmPpG1DU1nvK/A4HjcIR4WL7MKanRtAi/+dLfK0cIi5fWR2vNuUAxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"473f715c5b768b8db06bcb3ebb7713e59d5a6bcb94a2eb65b5bf75fc707495c0","last_reissued_at":"2026-05-18T00:40:28.285501Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:28.285501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference-driven Similarity Join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chuancong Gao, Jiannan Wang, Jian Pei, Rui Li, Yi Chang","submitted_at":"2017-06-13T21:59:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04266","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1706.04266","created_at":"2026-05-18T00:40:28.285569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04266v3","created_at":"2026-05-18T00:40:28.285569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04266","created_at":"2026-05-18T00:40:28.285569+00:00"},{"alias_kind":"pith_short_12","alias_value":"I47XCXC3O2FY","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"I47XCXC3O2FY3MDL","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"I47XCXC3","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W","json":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W.json","graph_json":"https://pith.science/api/pith-number/I47XCXC3O2FY3MDLZM7LW5YT4W/graph.json","events_json":"https://pith.science/api/pith-number/I47XCXC3O2FY3MDLZM7LW5YT4W/events.json","paper":"https://pith.science/paper/I47XCXC3"},"agent_actions":{"view_html":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W","download_json":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W.json","view_paper":"https://pith.science/paper/I47XCXC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04266&json=true","fetch_graph":"https://pith.science/api/pith-number/I47XCXC3O2FY3MDLZM7LW5YT4W/graph.json","fetch_events":"https://pith.science/api/pith-number/I47XCXC3O2FY3MDLZM7LW5YT4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W/action/storage_attestation","attest_author":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W/action/author_attestation","sign_citation":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W/action/citation_signature","submit_replication":"https://pith.science/pith/I47XCXC3O2FY3MDLZM7LW5YT4W/action/replication_record"}},"created_at":"2026-05-18T00:40:28.285569+00:00","updated_at":"2026-05-18T00:40:28.285569+00:00"}