{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UVRUZIUCA6O6Q6WRLZ2Y75CBWT","short_pith_number":"pith:UVRUZIUC","schema_version":"1.0","canonical_sha256":"a5634ca282079de87ad15e758ff441b4d2d7a17081b40b66f2896e09884f2ecf","source":{"kind":"arxiv","id":"2605.24308","version":1},"attestation_state":"computed","paper":{"title":"LEARNT: A Practical Estimator for Cardinality of LIKE Queries with Formal Accuracy Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Divesh Srivastava, Hai Lan, Shixun Huang, Yang Yu, Yuwei Peng, Zhifeng Bao","submitted_at":"2026-05-23T00:36:47Z","abstract_excerpt":"We study the problem of cardinality estimation for LIKE queries on string data, focusing on the most common patterns in real workloads: prefix, suffix, and substring queries. We propose LEARNT, a LIKE query Estimator with Accuracy, Robustness, Negligible overhead, Tunability, and Theoretical guarantees. LEARNT formulates estimation as a bucket-classification problem, and upon correct classification, it yields formal bounds on Q-error for the queries with non-empty answer. It employs a memory-efficient bucketed layered-filter architecture with Bloom filters and compact auxiliary tables, togethe"},"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":"2605.24308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-05-23T00:36:47Z","cross_cats_sorted":[],"title_canon_sha256":"f862e94d5671ca9a327498e78502cb655d63b9f7867cd242dd0baf5e73f18932","abstract_canon_sha256":"a6472e8cc5484e82167f6d8b5418eb032dffaf7536fbc51e285e49b8bcbe510d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:59.025417Z","signature_b64":"C6ebo67kV6i6Foum8Aik+ofHzUKP9WRSdPo4qsI61kfUYY+jKJlzY0vmjWjFPjHTPuvxrROIWTg9EtdKtv4JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5634ca282079de87ad15e758ff441b4d2d7a17081b40b66f2896e09884f2ecf","last_reissued_at":"2026-05-26T01:02:59.024576Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:59.024576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEARNT: A Practical Estimator for Cardinality of LIKE Queries with Formal Accuracy Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Divesh Srivastava, Hai Lan, Shixun Huang, Yang Yu, Yuwei Peng, Zhifeng Bao","submitted_at":"2026-05-23T00:36:47Z","abstract_excerpt":"We study the problem of cardinality estimation for LIKE queries on string data, focusing on the most common patterns in real workloads: prefix, suffix, and substring queries. We propose LEARNT, a LIKE query Estimator with Accuracy, Robustness, Negligible overhead, Tunability, and Theoretical guarantees. LEARNT formulates estimation as a bucket-classification problem, and upon correct classification, it yields formal bounds on Q-error for the queries with non-empty answer. It employs a memory-efficient bucketed layered-filter architecture with Bloom filters and compact auxiliary tables, togethe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24308","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.24308/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":"2605.24308","created_at":"2026-05-26T01:02:59.024708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24308v1","created_at":"2026-05-26T01:02:59.024708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24308","created_at":"2026-05-26T01:02:59.024708+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVRUZIUCA6O6","created_at":"2026-05-26T01:02:59.024708+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVRUZIUCA6O6Q6WR","created_at":"2026-05-26T01:02:59.024708+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVRUZIUC","created_at":"2026-05-26T01:02:59.024708+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/UVRUZIUCA6O6Q6WRLZ2Y75CBWT","json":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT.json","graph_json":"https://pith.science/api/pith-number/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/graph.json","events_json":"https://pith.science/api/pith-number/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/events.json","paper":"https://pith.science/paper/UVRUZIUC"},"agent_actions":{"view_html":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT","download_json":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT.json","view_paper":"https://pith.science/paper/UVRUZIUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24308&json=true","fetch_graph":"https://pith.science/api/pith-number/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/graph.json","fetch_events":"https://pith.science/api/pith-number/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/action/storage_attestation","attest_author":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/action/author_attestation","sign_citation":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/action/citation_signature","submit_replication":"https://pith.science/pith/UVRUZIUCA6O6Q6WRLZ2Y75CBWT/action/replication_record"}},"created_at":"2026-05-26T01:02:59.024708+00:00","updated_at":"2026-05-26T01:02:59.024708+00:00"}