{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7NIIOLIX5UEXR4X5WFFXZAFGS4","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":"8963b9d94b5db74d149322c658e172f7bfae6b839931f08b227b63989168d700","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-31T07:53:10Z","title_canon_sha256":"b8c2760e8debc8cac21ebd337d0cefb41a3c054f88947e26d23bcd29bfab3d3f"},"schema_version":"1.0","source":{"id":"2001.11692","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.11692","created_at":"2026-07-05T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2001.11692v3","created_at":"2026-07-05T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.11692","created_at":"2026-07-05T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"7NIIOLIX5UEX","created_at":"2026-07-05T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"7NIIOLIX5UEXR4X5","created_at":"2026-07-05T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"7NIIOLIX","created_at":"2026-07-05T01:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:a5331ed3759f8bb5b02f54dad451df5d2177bdc986d950886584c3fbae9adbcb","target":"graph","created_at":"2026-07-05T01:05:00Z","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/2001.11692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Edit-distance-based string similarity search has many applications such as spell correction, data de-duplication, and sequence alignment. However, computing edit distance is known to have high complexity, which makes string similarity search challenging for large datasets. In this paper, we propose a deep learning pipeline (called CNN-ED) that embeds edit distance into Euclidean distance for fast approximate similarity search. A convolutional neural network (CNN) is used to generate fixed-length vector embeddings for a dataset of strings and the loss function is a combination of the triplet lo","authors_text":"Han Yang, James Cheng, Kaiwen Zhou, Xiao Yan, Xinyan Dai, Yuxuan Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-31T07:53:10Z","title":"Convolutional Embedding for Edit Distance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.11692","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":"sha256:62306b5f81d08da8d91691c57d2054e3e8ab9a77ae05ec9720d0b9d08810ef24","target":"record","created_at":"2026-07-05T01:05:00Z","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":"8963b9d94b5db74d149322c658e172f7bfae6b839931f08b227b63989168d700","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-31T07:53:10Z","title_canon_sha256":"b8c2760e8debc8cac21ebd337d0cefb41a3c054f88947e26d23bcd29bfab3d3f"},"schema_version":"1.0","source":{"id":"2001.11692","kind":"arxiv","version":3}},"canonical_sha256":"fb50872d17ed0978f2fdb14b7c80a69734c396810ed112c1c90a04dcae7a6623","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb50872d17ed0978f2fdb14b7c80a69734c396810ed112c1c90a04dcae7a6623","first_computed_at":"2026-07-05T01:05:00.977770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:00.977770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RzPupnIy7gkZtAWw2iEgyGw99bR3PJa+02jnmr+dMCwhZrRsPqQ/5psPCKbMyhAjHusqjGeznz+dtT2FfA4NAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:00.978237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.11692","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62306b5f81d08da8d91691c57d2054e3e8ab9a77ae05ec9720d0b9d08810ef24","sha256:a5331ed3759f8bb5b02f54dad451df5d2177bdc986d950886584c3fbae9adbcb"],"state_sha256":"1b93d1cd18c4c56054e2b664cc98e7d24b9736f4686c01c89ab4632cd4379990"}