{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7RA4QSHYBERBQJJBMHLCCCYVKR","short_pith_number":"pith:7RA4QSHY","canonical_record":{"source":{"id":"1810.12123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-29T13:42:10Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"a5d7406407f75c459a0a25616aac27b35b0d0435b5a1cdd687e38ed49e5d5b70","abstract_canon_sha256":"ea810f724a78a20cc34e8209161aff966190f7da237609a3f20811f48fbf7e41"},"schema_version":"1.0"},"canonical_sha256":"fc41c848f8092218252161d6210b15544abeb85d890eb48fb24d0b9007610320","source":{"kind":"arxiv","id":"1810.12123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12123","created_at":"2026-05-18T00:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12123v1","created_at":"2026-05-18T00:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12123","created_at":"2026-05-18T00:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"7RA4QSHYBERB","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RA4QSHYBERBQJJB","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RA4QSHY","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7RA4QSHYBERBQJJBMHLCCCYVKR","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-29T13:42:10Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"a5d7406407f75c459a0a25616aac27b35b0d0435b5a1cdd687e38ed49e5d5b70","abstract_canon_sha256":"ea810f724a78a20cc34e8209161aff966190f7da237609a3f20811f48fbf7e41"},"schema_version":"1.0"},"canonical_sha256":"fc41c848f8092218252161d6210b15544abeb85d890eb48fb24d0b9007610320","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:04.236973Z","signature_b64":"YNSTV2KnuKEvmsfWvYFHp5Y1Cpd/3M6vKbOoGFv9KLUFgnwO52AfGwa3+HRvaSpBHp8Mi7vt4aKd+ry8J6/rBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc41c848f8092218252161d6210b15544abeb85d890eb48fb24d0b9007610320","last_reissued_at":"2026-05-18T00:02:04.236350Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:04.236350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12123","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":"2026-05-18T00:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ayZWyR71VEOmzgXCBs9jxXjKELV/Ey2lE96TK7di8Fn9rxWqJik+2v9aCqGR/ADaR082GBd8WjM6GtVcF3lCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:18:49.056784Z"},"content_sha256":"d07bd7b4d5670322a5bb6d78feb511bd56c4bdf7d079df6b9d03f04f1409ca28","schema_version":"1.0","event_id":"sha256:d07bd7b4d5670322a5bb6d78feb511bd56c4bdf7d079df6b9d03f04f1409ca28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7RA4QSHYBERBQJJBMHLCCCYVKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Taxonomic Similarity Joins with Adaptive Overlap Constraint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Jiaheng Lu, Pengfei Xu","submitted_at":"2018-10-29T13:42:10Z","abstract_excerpt":"A similarity join aims to find all similar pairs between two collections of records. Established approaches usually deal with synthetic differences like typos and abbreviations, but neglect the semantic relations between words. Such relations, however, are helpful for obtaining high-quality joining results. In this paper, we leverage the taxonomy knowledge (i.e., a set of IS-A hierarchical relations) to define a similarity measure which finds semantic-similar records from two datasets. Based on this measure, we develop a similarity join algorithm with prefix filtering framework to prune away i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12123","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":"2026-05-18T00:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nHgosm8a7nrJNRdLYYMQDL0fYTdk+9ZKH29knH72vTYuRE2RPfoZ8XajHERouaL7BT4dRP47MnuJJsxjiB0GCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:18:49.057131Z"},"content_sha256":"ce2a9b38d04f2e5c06ee4d20a1f5fe3117a0c7be059624b380503a38c2918bdf","schema_version":"1.0","event_id":"sha256:ce2a9b38d04f2e5c06ee4d20a1f5fe3117a0c7be059624b380503a38c2918bdf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RA4QSHYBERBQJJBMHLCCCYVKR/bundle.json","state_url":"https://pith.science/pith/7RA4QSHYBERBQJJBMHLCCCYVKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RA4QSHYBERBQJJBMHLCCCYVKR/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":"2026-06-26T10:18:49Z","links":{"resolver":"https://pith.science/pith/7RA4QSHYBERBQJJBMHLCCCYVKR","bundle":"https://pith.science/pith/7RA4QSHYBERBQJJBMHLCCCYVKR/bundle.json","state":"https://pith.science/pith/7RA4QSHYBERBQJJBMHLCCCYVKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RA4QSHYBERBQJJBMHLCCCYVKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7RA4QSHYBERBQJJBMHLCCCYVKR","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":"ea810f724a78a20cc34e8209161aff966190f7da237609a3f20811f48fbf7e41","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-29T13:42:10Z","title_canon_sha256":"a5d7406407f75c459a0a25616aac27b35b0d0435b5a1cdd687e38ed49e5d5b70"},"schema_version":"1.0","source":{"id":"1810.12123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12123","created_at":"2026-05-18T00:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12123v1","created_at":"2026-05-18T00:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12123","created_at":"2026-05-18T00:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"7RA4QSHYBERB","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RA4QSHYBERBQJJB","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RA4QSHY","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:ce2a9b38d04f2e5c06ee4d20a1f5fe3117a0c7be059624b380503a38c2918bdf","target":"graph","created_at":"2026-05-18T00:02:04Z","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":"A similarity join aims to find all similar pairs between two collections of records. Established approaches usually deal with synthetic differences like typos and abbreviations, but neglect the semantic relations between words. Such relations, however, are helpful for obtaining high-quality joining results. In this paper, we leverage the taxonomy knowledge (i.e., a set of IS-A hierarchical relations) to define a similarity measure which finds semantic-similar records from two datasets. Based on this measure, we develop a similarity join algorithm with prefix filtering framework to prune away i","authors_text":"Jiaheng Lu, Pengfei Xu","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-29T13:42:10Z","title":"Efficient Taxonomic Similarity Joins with Adaptive Overlap Constraint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12123","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:d07bd7b4d5670322a5bb6d78feb511bd56c4bdf7d079df6b9d03f04f1409ca28","target":"record","created_at":"2026-05-18T00:02:04Z","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":"ea810f724a78a20cc34e8209161aff966190f7da237609a3f20811f48fbf7e41","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-29T13:42:10Z","title_canon_sha256":"a5d7406407f75c459a0a25616aac27b35b0d0435b5a1cdd687e38ed49e5d5b70"},"schema_version":"1.0","source":{"id":"1810.12123","kind":"arxiv","version":1}},"canonical_sha256":"fc41c848f8092218252161d6210b15544abeb85d890eb48fb24d0b9007610320","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc41c848f8092218252161d6210b15544abeb85d890eb48fb24d0b9007610320","first_computed_at":"2026-05-18T00:02:04.236350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:04.236350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YNSTV2KnuKEvmsfWvYFHp5Y1Cpd/3M6vKbOoGFv9KLUFgnwO52AfGwa3+HRvaSpBHp8Mi7vt4aKd+ry8J6/rBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:04.236973Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d07bd7b4d5670322a5bb6d78feb511bd56c4bdf7d079df6b9d03f04f1409ca28","sha256:ce2a9b38d04f2e5c06ee4d20a1f5fe3117a0c7be059624b380503a38c2918bdf"],"state_sha256":"82827c79d835cbe4ba8b9ce94155fda2c0c25dcf682a41a1cf15d1cc7fb5c467"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Hric3QeCu4f+F24e9tWLBQr54KHTJmqVXAjC+b7D7Mpt5P+x7gnohYScBbX32WtDct6ZLIAiCCWOw0Y6+emDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T10:18:49.059057Z","bundle_sha256":"adb972602fe18ff39bc4bd29b9fd60ddc5d8759984d09cffb0d0ca73bea521cd"}}