{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M5ZFLETWPVZFSZCKUHQXRC6DZS","short_pith_number":"pith:M5ZFLETW","schema_version":"1.0","canonical_sha256":"67725592767d7259644aa1e1788bc3ccae130852d2cc3e5f34ae07d4c9c22d7d","source":{"kind":"arxiv","id":"2507.07438","version":1},"attestation_state":"computed","paper":{"title":"Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dong Wang, Hongzhi Wang, Kaixing Zhang, Xianglong Liu, Yiming Guan, Yingze Li, Zixuan Wang","submitted_at":"2025-07-10T05:29:04Z","abstract_excerpt":"Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment. This work is the first to theoretical investigate how minimal data-level drifts can maximally degrade the accuracy of learned estimators. We propose data-centric algorithmic complexity attacks against learned estimators in a black-box setting, proving that finding the optimal attack strategy is NP-Hard. To address this, we design a polynomial-time approximation algorithm with a $(1-\\kappa)$ approximation ratio. Exte"},"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":"2507.07438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-10T05:29:04Z","cross_cats_sorted":[],"title_canon_sha256":"f8fc12fb622ff1ffeb7ba815a9bcfc9e5e300be643b43f266b401e955f67c3e6","abstract_canon_sha256":"c1354a4de30f9581d4b4d147f3835b247a4b09b08e43f083f475770d353ac36b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:58.021274Z","signature_b64":"SnxsNHUl2AcyJLhDcZCJ2RmjOgq7FlHBuLWcGqs/gEy+xhMxbEBWnRUZb9glkQrxDLYi1P+rXssvYYtdWWxRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67725592767d7259644aa1e1788bc3ccae130852d2cc3e5f34ae07d4c9c22d7d","last_reissued_at":"2026-07-05T11:34:58.020769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:58.020769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dong Wang, Hongzhi Wang, Kaixing Zhang, Xianglong Liu, Yiming Guan, Yingze Li, Zixuan Wang","submitted_at":"2025-07-10T05:29:04Z","abstract_excerpt":"Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment. This work is the first to theoretical investigate how minimal data-level drifts can maximally degrade the accuracy of learned estimators. We propose data-centric algorithmic complexity attacks against learned estimators in a black-box setting, proving that finding the optimal attack strategy is NP-Hard. To address this, we design a polynomial-time approximation algorithm with a $(1-\\kappa)$ approximation ratio. Exte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07438","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/2507.07438/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":"2507.07438","created_at":"2026-07-05T11:34:58.020831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07438v1","created_at":"2026-07-05T11:34:58.020831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07438","created_at":"2026-07-05T11:34:58.020831+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5ZFLETWPVZF","created_at":"2026-07-05T11:34:58.020831+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5ZFLETWPVZFSZCK","created_at":"2026-07-05T11:34:58.020831+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5ZFLETW","created_at":"2026-07-05T11:34:58.020831+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/M5ZFLETWPVZFSZCKUHQXRC6DZS","json":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS.json","graph_json":"https://pith.science/api/pith-number/M5ZFLETWPVZFSZCKUHQXRC6DZS/graph.json","events_json":"https://pith.science/api/pith-number/M5ZFLETWPVZFSZCKUHQXRC6DZS/events.json","paper":"https://pith.science/paper/M5ZFLETW"},"agent_actions":{"view_html":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS","download_json":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS.json","view_paper":"https://pith.science/paper/M5ZFLETW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07438&json=true","fetch_graph":"https://pith.science/api/pith-number/M5ZFLETWPVZFSZCKUHQXRC6DZS/graph.json","fetch_events":"https://pith.science/api/pith-number/M5ZFLETWPVZFSZCKUHQXRC6DZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS/action/storage_attestation","attest_author":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS/action/author_attestation","sign_citation":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS/action/citation_signature","submit_replication":"https://pith.science/pith/M5ZFLETWPVZFSZCKUHQXRC6DZS/action/replication_record"}},"created_at":"2026-07-05T11:34:58.020831+00:00","updated_at":"2026-07-05T11:34:58.020831+00:00"}