{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:TUDDAWNV5DOC7GOCNHBLTYLZVK","short_pith_number":"pith:TUDDAWNV","canonical_record":{"source":{"id":"1702.00093","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-01T00:39:18Z","cross_cats_sorted":[],"title_canon_sha256":"3746d261735611e7eb8082d0cd1b0a1707bdb37a61a050fdd5a1295db5da7fb0","abstract_canon_sha256":"4dc0f04c847a588a7bc1a01f73eeae5ee56352cd92021dbef26e6ed772e5bac1"},"schema_version":"1.0"},"canonical_sha256":"9d063059b5e8dc2f99c269c2b9e179aa877b532ff5751dde86996791f0ca78ff","source":{"kind":"arxiv","id":"1702.00093","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00093","created_at":"2026-05-18T00:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00093v3","created_at":"2026-05-18T00:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00093","created_at":"2026-05-18T00:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"TUDDAWNV5DOC","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TUDDAWNV5DOC7GOC","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TUDDAWNV","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:TUDDAWNV5DOC7GOCNHBLTYLZVK","target":"record","payload":{"canonical_record":{"source":{"id":"1702.00093","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-01T00:39:18Z","cross_cats_sorted":[],"title_canon_sha256":"3746d261735611e7eb8082d0cd1b0a1707bdb37a61a050fdd5a1295db5da7fb0","abstract_canon_sha256":"4dc0f04c847a588a7bc1a01f73eeae5ee56352cd92021dbef26e6ed772e5bac1"},"schema_version":"1.0"},"canonical_sha256":"9d063059b5e8dc2f99c269c2b9e179aa877b532ff5751dde86996791f0ca78ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:32.257268Z","signature_b64":"w0ZKnwqDiAkWAWF9tugRDiDrzs3dvJDA0kSh7gKCKoKCzl+XkRhv/iF/ep9itAq1GmbjZda4gOpuBfZHDhTqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d063059b5e8dc2f99c269c2b9e179aa877b532ff5751dde86996791f0ca78ff","last_reissued_at":"2026-05-18T00:33:32.256856Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:32.256856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.00093","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"laJtGQF2SOehye4UpXLspDZEte002pXWsxfb/OlxS7zBYelhU7wO2N3AIR16D8gTPd+rRGg8yHprwIhVqckgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:20:50.981801Z"},"content_sha256":"bb934c885ac60684afb2c9b23577258ceea15d7d63594a81b642e0801674bc5e","schema_version":"1.0","event_id":"sha256:bb934c885ac60684afb2c9b23577258ceea15d7d63594a81b642e0801674bc5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:TUDDAWNV5DOC7GOCNHBLTYLZVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EmbedJoin: Efficient Edit Similarity Joins via Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Haoyu Zhang, Qin Zhang","submitted_at":"2017-02-01T00:39:18Z","abstract_excerpt":"We study the problem of edit similarity joins, where given a set of strings and a threshold value $K$, we want to output all pairs of strings whose edit distances are at most $K$. Edit similarity join is a fundamental problem in data cleaning/integration, bioinformatics, collaborative filtering and natural language processing, and has been identified as a primitive operator for database systems. This problem has been studied extensively in the literature. However, we have observed that all the existing algorithms fall short on long strings and large distance thresholds.\n  In this paper we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00093","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAUr7XpP0RIqC3jnc6zA9tMMZgaubj/IHevG1TnIdEGZ5lQwp2ki90dN6owNIMLSD6FxjTic+uVXgFM5L3VUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:20:50.982484Z"},"content_sha256":"baf7dea60f28c11e3014e4fcd01afc8f7d67c90ab6eef62e3bfe7f70c18f2e4c","schema_version":"1.0","event_id":"sha256:baf7dea60f28c11e3014e4fcd01afc8f7d67c90ab6eef62e3bfe7f70c18f2e4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK/bundle.json","state_url":"https://pith.science/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK/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":"2026-05-31T14:20:50Z","links":{"resolver":"https://pith.science/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK","bundle":"https://pith.science/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK/bundle.json","state":"https://pith.science/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUDDAWNV5DOC7GOCNHBLTYLZVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TUDDAWNV5DOC7GOCNHBLTYLZVK","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":"4dc0f04c847a588a7bc1a01f73eeae5ee56352cd92021dbef26e6ed772e5bac1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-01T00:39:18Z","title_canon_sha256":"3746d261735611e7eb8082d0cd1b0a1707bdb37a61a050fdd5a1295db5da7fb0"},"schema_version":"1.0","source":{"id":"1702.00093","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00093","created_at":"2026-05-18T00:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00093v3","created_at":"2026-05-18T00:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00093","created_at":"2026-05-18T00:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"TUDDAWNV5DOC","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TUDDAWNV5DOC7GOC","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TUDDAWNV","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:baf7dea60f28c11e3014e4fcd01afc8f7d67c90ab6eef62e3bfe7f70c18f2e4c","target":"graph","created_at":"2026-05-18T00:33:32Z","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":"We study the problem of edit similarity joins, where given a set of strings and a threshold value $K$, we want to output all pairs of strings whose edit distances are at most $K$. Edit similarity join is a fundamental problem in data cleaning/integration, bioinformatics, collaborative filtering and natural language processing, and has been identified as a primitive operator for database systems. This problem has been studied extensively in the literature. However, we have observed that all the existing algorithms fall short on long strings and large distance thresholds.\n  In this paper we prop","authors_text":"Haoyu Zhang, Qin Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-01T00:39:18Z","title":"EmbedJoin: Efficient Edit Similarity Joins via Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00093","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:bb934c885ac60684afb2c9b23577258ceea15d7d63594a81b642e0801674bc5e","target":"record","created_at":"2026-05-18T00:33:32Z","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":"4dc0f04c847a588a7bc1a01f73eeae5ee56352cd92021dbef26e6ed772e5bac1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-01T00:39:18Z","title_canon_sha256":"3746d261735611e7eb8082d0cd1b0a1707bdb37a61a050fdd5a1295db5da7fb0"},"schema_version":"1.0","source":{"id":"1702.00093","kind":"arxiv","version":3}},"canonical_sha256":"9d063059b5e8dc2f99c269c2b9e179aa877b532ff5751dde86996791f0ca78ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d063059b5e8dc2f99c269c2b9e179aa877b532ff5751dde86996791f0ca78ff","first_computed_at":"2026-05-18T00:33:32.256856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:32.256856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w0ZKnwqDiAkWAWF9tugRDiDrzs3dvJDA0kSh7gKCKoKCzl+XkRhv/iF/ep9itAq1GmbjZda4gOpuBfZHDhTqBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:32.257268Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.00093","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb934c885ac60684afb2c9b23577258ceea15d7d63594a81b642e0801674bc5e","sha256:baf7dea60f28c11e3014e4fcd01afc8f7d67c90ab6eef62e3bfe7f70c18f2e4c"],"state_sha256":"e3690e78e433af90615f6b41bfc936fa7d725fa6bda53cf759de80c264bb9f3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7i6OYGdBLuCn8DGyPFG/KOoSl4H56wEuCW/ZXQoKL65an3n3YZqeisRc5A3yrgd9Z7YuZjmeWValU8Ebd0ABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T14:20:50.986249Z","bundle_sha256":"3b5881958192ffe767b9b561694a25600b8e37dffd4f3833ed1bf70d35032048"}}