{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6UF6O66OSU3QF5JYORJVJA6PDA","short_pith_number":"pith:6UF6O66O","schema_version":"1.0","canonical_sha256":"f50be77bce953702f53874535483cf1806c56cd41c4c858d7d06f4d90453bbd8","source":{"kind":"arxiv","id":"2606.23081","version":1},"attestation_state":"computed","paper":{"title":"SemCEB: A Cardinality Estimation Benchmark for Semantic Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andreas Kipf, Andreas Zimmerer, Claudius K\\\"uhn, Mihail Stoian, Renata Borovica-Gajic, Yang Li","submitted_at":"2026-06-22T09:30:24Z","abstract_excerpt":"Modern data systems increasingly expose multi-modal large language models as semantic operators: SQL operators, including filters and joins, whose predicates are defined by a natural-language instruction. Query optimization in these systems still rests on the same foundations as in traditional databases$\\unicode{x2013}$plan enumeration and cost models$\\unicode{x2013}$yet faces new challenges, e.g., a larger plan space and the lack of efficient cardinality estimates. The elevated per-tuple costs of semantic operators make bad plan choices worse by orders of magnitude. Therefore, precise$\\unicod"},"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":"2606.23081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-22T09:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"5aa37432d2216903961dd5d86cb3907de3fa702c4f55f97fbd5ee4d56ee8f88d","abstract_canon_sha256":"6582bc26aafd77c51db7845550702fc18d4000a3e06a57a1040b95025ffd3b42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:09.327730Z","signature_b64":"dVm6EWQhtYhLkmAq6h/J9F4rFuxlrFMlRnlwf3Xal87i7T1Zz5l603Gd3N/sLRpZkCx9Dr4Vge8P7z2o8sRlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f50be77bce953702f53874535483cf1806c56cd41c4c858d7d06f4d90453bbd8","last_reissued_at":"2026-06-23T03:14:09.327339Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:09.327339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemCEB: A Cardinality Estimation Benchmark for Semantic Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andreas Kipf, Andreas Zimmerer, Claudius K\\\"uhn, Mihail Stoian, Renata Borovica-Gajic, Yang Li","submitted_at":"2026-06-22T09:30:24Z","abstract_excerpt":"Modern data systems increasingly expose multi-modal large language models as semantic operators: SQL operators, including filters and joins, whose predicates are defined by a natural-language instruction. Query optimization in these systems still rests on the same foundations as in traditional databases$\\unicode{x2013}$plan enumeration and cost models$\\unicode{x2013}$yet faces new challenges, e.g., a larger plan space and the lack of efficient cardinality estimates. The elevated per-tuple costs of semantic operators make bad plan choices worse by orders of magnitude. Therefore, precise$\\unicod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23081","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/2606.23081/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":"2606.23081","created_at":"2026-06-23T03:14:09.327396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23081v1","created_at":"2026-06-23T03:14:09.327396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23081","created_at":"2026-06-23T03:14:09.327396+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UF6O66OSU3Q","created_at":"2026-06-23T03:14:09.327396+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UF6O66OSU3QF5JY","created_at":"2026-06-23T03:14:09.327396+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UF6O66O","created_at":"2026-06-23T03:14:09.327396+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/6UF6O66OSU3QF5JYORJVJA6PDA","json":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA.json","graph_json":"https://pith.science/api/pith-number/6UF6O66OSU3QF5JYORJVJA6PDA/graph.json","events_json":"https://pith.science/api/pith-number/6UF6O66OSU3QF5JYORJVJA6PDA/events.json","paper":"https://pith.science/paper/6UF6O66O"},"agent_actions":{"view_html":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA","download_json":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA.json","view_paper":"https://pith.science/paper/6UF6O66O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23081&json=true","fetch_graph":"https://pith.science/api/pith-number/6UF6O66OSU3QF5JYORJVJA6PDA/graph.json","fetch_events":"https://pith.science/api/pith-number/6UF6O66OSU3QF5JYORJVJA6PDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA/action/storage_attestation","attest_author":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA/action/author_attestation","sign_citation":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA/action/citation_signature","submit_replication":"https://pith.science/pith/6UF6O66OSU3QF5JYORJVJA6PDA/action/replication_record"}},"created_at":"2026-06-23T03:14:09.327396+00:00","updated_at":"2026-06-23T03:14:09.327396+00:00"}