{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZZCORJITPVS7LI7J6GN6FRMRSM","short_pith_number":"pith:ZZCORJIT","schema_version":"1.0","canonical_sha256":"ce44e8a5137d65f5a3e9f19be2c5919321f8659bb37c16b219da385d63e96243","source":{"kind":"arxiv","id":"2607.00868","version":1},"attestation_state":"computed","paper":{"title":"From Single to Multiple Attributes: Experimental Insights on Sampling-Based Distinct Combination Estimation in GROUP-BY Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bin Wang, Xiaochun Yang, Yuan Sui, Yujie Zhang","submitted_at":"2026-07-01T12:33:00Z","abstract_excerpt":"Estimating the number of distinct combinations in multi-attribute GROUP-BY queries remains a significant yet underexplored challenge. Current cardinality estimation techniques primarily focus on SPJ queries (i.e., selections, projections, and joins) and neglect GROUP-BY operations; meanwhile, distinct value estimation research has mainly targeted the single-attribute setting. Although sampling-based methods, including recent approaches with learned models, can theoretically support multi-attribute estimation, their practical effectiveness remains unclear. A comprehensive empirical evaluation i"},"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":"2607.00868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-01T12:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"7b8612fc63b140fa1f066efb994979fcc36a8ec46b5635a9adbb0fed741d2316","abstract_canon_sha256":"718417d6b5f5b35640fdb7b6067d38d9883a0aa70f20f85e0dffbf63bd7777d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:21.836264Z","signature_b64":"Za6xJqoc04zocKMaH2F+er4SmgH3UnPTMfQSs8d+rsFal2/SJQOlChXevbnaTLr0YlCC1ihUFD8Lhatk4yzaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce44e8a5137d65f5a3e9f19be2c5919321f8659bb37c16b219da385d63e96243","last_reissued_at":"2026-07-02T01:18:21.835908Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:21.835908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Single to Multiple Attributes: Experimental Insights on Sampling-Based Distinct Combination Estimation in GROUP-BY Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bin Wang, Xiaochun Yang, Yuan Sui, Yujie Zhang","submitted_at":"2026-07-01T12:33:00Z","abstract_excerpt":"Estimating the number of distinct combinations in multi-attribute GROUP-BY queries remains a significant yet underexplored challenge. Current cardinality estimation techniques primarily focus on SPJ queries (i.e., selections, projections, and joins) and neglect GROUP-BY operations; meanwhile, distinct value estimation research has mainly targeted the single-attribute setting. Although sampling-based methods, including recent approaches with learned models, can theoretically support multi-attribute estimation, their practical effectiveness remains unclear. A comprehensive empirical evaluation i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00868","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/2607.00868/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":"2607.00868","created_at":"2026-07-02T01:18:21.835973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00868v1","created_at":"2026-07-02T01:18:21.835973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00868","created_at":"2026-07-02T01:18:21.835973+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZCORJITPVS7","created_at":"2026-07-02T01:18:21.835973+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZCORJITPVS7LI7J","created_at":"2026-07-02T01:18:21.835973+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZCORJIT","created_at":"2026-07-02T01:18:21.835973+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/ZZCORJITPVS7LI7J6GN6FRMRSM","json":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM.json","graph_json":"https://pith.science/api/pith-number/ZZCORJITPVS7LI7J6GN6FRMRSM/graph.json","events_json":"https://pith.science/api/pith-number/ZZCORJITPVS7LI7J6GN6FRMRSM/events.json","paper":"https://pith.science/paper/ZZCORJIT"},"agent_actions":{"view_html":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM","download_json":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM.json","view_paper":"https://pith.science/paper/ZZCORJIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00868&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZCORJITPVS7LI7J6GN6FRMRSM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZCORJITPVS7LI7J6GN6FRMRSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM/action/storage_attestation","attest_author":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM/action/author_attestation","sign_citation":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM/action/citation_signature","submit_replication":"https://pith.science/pith/ZZCORJITPVS7LI7J6GN6FRMRSM/action/replication_record"}},"created_at":"2026-07-02T01:18:21.835973+00:00","updated_at":"2026-07-02T01:18:21.835973+00:00"}