{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7NIIOLIX5UEXR4X5WFFXZAFGS4","short_pith_number":"pith:7NIIOLIX","schema_version":"1.0","canonical_sha256":"fb50872d17ed0978f2fdb14b7c80a69734c396810ed112c1c90a04dcae7a6623","source":{"kind":"arxiv","id":"2001.11692","version":3},"attestation_state":"computed","paper":{"title":"Convolutional Embedding for Edit Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Han Yang, James Cheng, Kaiwen Zhou, Xiao Yan, Xinyan Dai, Yuxuan Wang","submitted_at":"2020-01-31T07:53:10Z","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"},"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":"2001.11692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-31T07:53:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8c2760e8debc8cac21ebd337d0cefb41a3c054f88947e26d23bcd29bfab3d3f","abstract_canon_sha256":"8963b9d94b5db74d149322c658e172f7bfae6b839931f08b227b63989168d700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:00.978237Z","signature_b64":"RzPupnIy7gkZtAWw2iEgyGw99bR3PJa+02jnmr+dMCwhZrRsPqQ/5psPCKbMyhAjHusqjGeznz+dtT2FfA4NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb50872d17ed0978f2fdb14b7c80a69734c396810ed112c1c90a04dcae7a6623","last_reissued_at":"2026-07-05T01:05:00.977770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:00.977770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Embedding for Edit Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Han Yang, James Cheng, Kaiwen Zhou, Xiao Yan, Xinyan Dai, Yuxuan Wang","submitted_at":"2020-01-31T07:53:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.11692","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.11692/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2001.11692","created_at":"2026-07-05T01:05:00.977825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.11692v3","created_at":"2026-07-05T01:05:00.977825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.11692","created_at":"2026-07-05T01:05:00.977825+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NIIOLIX5UEX","created_at":"2026-07-05T01:05:00.977825+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NIIOLIX5UEXR4X5","created_at":"2026-07-05T01:05:00.977825+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NIIOLIX","created_at":"2026-07-05T01:05:00.977825+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/7NIIOLIX5UEXR4X5WFFXZAFGS4","json":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4.json","graph_json":"https://pith.science/api/pith-number/7NIIOLIX5UEXR4X5WFFXZAFGS4/graph.json","events_json":"https://pith.science/api/pith-number/7NIIOLIX5UEXR4X5WFFXZAFGS4/events.json","paper":"https://pith.science/paper/7NIIOLIX"},"agent_actions":{"view_html":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4","download_json":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4.json","view_paper":"https://pith.science/paper/7NIIOLIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.11692&json=true","fetch_graph":"https://pith.science/api/pith-number/7NIIOLIX5UEXR4X5WFFXZAFGS4/graph.json","fetch_events":"https://pith.science/api/pith-number/7NIIOLIX5UEXR4X5WFFXZAFGS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4/action/storage_attestation","attest_author":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4/action/author_attestation","sign_citation":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4/action/citation_signature","submit_replication":"https://pith.science/pith/7NIIOLIX5UEXR4X5WFFXZAFGS4/action/replication_record"}},"created_at":"2026-07-05T01:05:00.977825+00:00","updated_at":"2026-07-05T01:05:00.977825+00:00"}