{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6Y7KGVQDADK6C7DO4JFWNSEPU","short_pith_number":"pith:M6Y7KGVQ","schema_version":"1.0","canonical_sha256":"67b1f51ab01806af0be377125b36447d18638b06f958d17023c956d542f6cd6f","source":{"kind":"arxiv","id":"2409.07014","version":3},"attestation_state":"computed","paper":{"title":"A Practical Theory of Generalization in Selectivity Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"stat.ML","authors_text":"Haoshu Xu, Peizhi Wu, Ryan Marcus, Zachary G. Ives","submitted_at":"2024-09-11T05:10:32Z","abstract_excerpt":"Query-driven machine learning models have emerged as a promising estimation technique for query selectivities. Yet, surprisingly little is known about the efficacy of these techniques from a theoretical perspective, as there exist substantial gaps between practical solutions and state-of-the-art (SOTA) theory based on the Probably Approximately Correct (PAC) learning framework. In this paper, we aim to bridge the gaps between theory and practice. First, we demonstrate that selectivity predictors induced by signed measures are learnable, which relaxes the reliance on probability measures in SOT"},"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":"2409.07014","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-09-11T05:10:32Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"9b484f06ddecbb5e79239949c6bdca5254b0418f47040f68456f53baac9caf79","abstract_canon_sha256":"1365fae22b501b7d0d24ebeb564bbb1e6d3ae309abde2d70ef10f0d58bca6871"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:02.922084Z","signature_b64":"g1oiSexZeh8ZQ3Z1cbT+aEuPm3bdGb3f7s+iJgRp3KVR1Ea/ONaDvDnyrRF/egu1yNQ4nd0NTLvzQHeV+Y3YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67b1f51ab01806af0be377125b36447d18638b06f958d17023c956d542f6cd6f","last_reissued_at":"2026-05-20T00:02:02.921240Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:02.921240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Practical Theory of Generalization in Selectivity Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"stat.ML","authors_text":"Haoshu Xu, Peizhi Wu, Ryan Marcus, Zachary G. Ives","submitted_at":"2024-09-11T05:10:32Z","abstract_excerpt":"Query-driven machine learning models have emerged as a promising estimation technique for query selectivities. Yet, surprisingly little is known about the efficacy of these techniques from a theoretical perspective, as there exist substantial gaps between practical solutions and state-of-the-art (SOTA) theory based on the Probably Approximately Correct (PAC) learning framework. In this paper, we aim to bridge the gaps between theory and practice. First, we demonstrate that selectivity predictors induced by signed measures are learnable, which relaxes the reliance on probability measures in SOT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07014","kind":"arxiv","version":3},"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/2409.07014/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":"2409.07014","created_at":"2026-05-20T00:02:02.921380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07014v3","created_at":"2026-05-20T00:02:02.921380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07014","created_at":"2026-05-20T00:02:02.921380+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6Y7KGVQDADK","created_at":"2026-05-20T00:02:02.921380+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6Y7KGVQDADK6C7D","created_at":"2026-05-20T00:02:02.921380+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6Y7KGVQ","created_at":"2026-05-20T00:02:02.921380+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/M6Y7KGVQDADK6C7DO4JFWNSEPU","json":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU.json","graph_json":"https://pith.science/api/pith-number/M6Y7KGVQDADK6C7DO4JFWNSEPU/graph.json","events_json":"https://pith.science/api/pith-number/M6Y7KGVQDADK6C7DO4JFWNSEPU/events.json","paper":"https://pith.science/paper/M6Y7KGVQ"},"agent_actions":{"view_html":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU","download_json":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU.json","view_paper":"https://pith.science/paper/M6Y7KGVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07014&json=true","fetch_graph":"https://pith.science/api/pith-number/M6Y7KGVQDADK6C7DO4JFWNSEPU/graph.json","fetch_events":"https://pith.science/api/pith-number/M6Y7KGVQDADK6C7DO4JFWNSEPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU/action/storage_attestation","attest_author":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU/action/author_attestation","sign_citation":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU/action/citation_signature","submit_replication":"https://pith.science/pith/M6Y7KGVQDADK6C7DO4JFWNSEPU/action/replication_record"}},"created_at":"2026-05-20T00:02:02.921380+00:00","updated_at":"2026-05-20T00:02:02.921380+00:00"}