{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LJFQ3LCRE2SZNUC3FXF6J3H4W3","short_pith_number":"pith:LJFQ3LCR","schema_version":"1.0","canonical_sha256":"5a4b0dac5126a596d05b2dcbe4ecfcb6eb93a6e46d4ababf064f8a1ea290ea18","source":{"kind":"arxiv","id":"2605.29093","version":1},"attestation_state":"computed","paper":{"title":"ScanTwin: Simulating Performance Regressions Without Access to Tenant Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Donghyun Sohn, Jennie Rogers","submitted_at":"2026-05-27T20:51:43Z","abstract_excerpt":"In cloud data platforms, developers often encounter performance regressions that occur in specific tenant datasets. However, due to confidentiality constraints, they cannot access the original data, which makes it difficult to reproduce these regressions locally. Current methods for synthetic data usually focus on statistical properties, such as matching data distributions or improving query accuracy. However, they overlook the physical properties that control how the engine behaves during scans, including row-group pruning.\n  We propose ScanTwin, a lightweight framework that extracts a per-ro"},"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":"2605.29093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-05-27T20:51:43Z","cross_cats_sorted":[],"title_canon_sha256":"27574a0fcc1c81e816876463ceccd1a760c037d941ee6e82bc00bb36a50d5890","abstract_canon_sha256":"0451204f1b736e6a9b9a1763a46a69967b7da4546275a6c860e91073bbb6607b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:17.893494Z","signature_b64":"bvTQJ0tixBt5pHj/at03SKSQvT98vCr4CAyp9NeGpdfEnZac1lscu12N/JTHV6UbfJkDBjJg7lNv4XO3Ku2rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a4b0dac5126a596d05b2dcbe4ecfcb6eb93a6e46d4ababf064f8a1ea290ea18","last_reissued_at":"2026-05-29T01:05:17.892533Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:17.892533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScanTwin: Simulating Performance Regressions Without Access to Tenant Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Donghyun Sohn, Jennie Rogers","submitted_at":"2026-05-27T20:51:43Z","abstract_excerpt":"In cloud data platforms, developers often encounter performance regressions that occur in specific tenant datasets. However, due to confidentiality constraints, they cannot access the original data, which makes it difficult to reproduce these regressions locally. Current methods for synthetic data usually focus on statistical properties, such as matching data distributions or improving query accuracy. However, they overlook the physical properties that control how the engine behaves during scans, including row-group pruning.\n  We propose ScanTwin, a lightweight framework that extracts a per-ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29093","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/2605.29093/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":"2605.29093","created_at":"2026-05-29T01:05:17.892676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29093v1","created_at":"2026-05-29T01:05:17.892676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29093","created_at":"2026-05-29T01:05:17.892676+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJFQ3LCRE2SZ","created_at":"2026-05-29T01:05:17.892676+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJFQ3LCRE2SZNUC3","created_at":"2026-05-29T01:05:17.892676+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJFQ3LCR","created_at":"2026-05-29T01:05:17.892676+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/LJFQ3LCRE2SZNUC3FXF6J3H4W3","json":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3.json","graph_json":"https://pith.science/api/pith-number/LJFQ3LCRE2SZNUC3FXF6J3H4W3/graph.json","events_json":"https://pith.science/api/pith-number/LJFQ3LCRE2SZNUC3FXF6J3H4W3/events.json","paper":"https://pith.science/paper/LJFQ3LCR"},"agent_actions":{"view_html":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3","download_json":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3.json","view_paper":"https://pith.science/paper/LJFQ3LCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29093&json=true","fetch_graph":"https://pith.science/api/pith-number/LJFQ3LCRE2SZNUC3FXF6J3H4W3/graph.json","fetch_events":"https://pith.science/api/pith-number/LJFQ3LCRE2SZNUC3FXF6J3H4W3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3/action/storage_attestation","attest_author":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3/action/author_attestation","sign_citation":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3/action/citation_signature","submit_replication":"https://pith.science/pith/LJFQ3LCRE2SZNUC3FXF6J3H4W3/action/replication_record"}},"created_at":"2026-05-29T01:05:17.892676+00:00","updated_at":"2026-05-29T01:05:17.892676+00:00"}