{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IX5FCSB3ODDYC3CDAP7TWP7WUQ","short_pith_number":"pith:IX5FCSB3","schema_version":"1.0","canonical_sha256":"45fa51483b70c7816c4303ff3b3ff6a40f76752cdedcc79a46b721ad60046fe5","source":{"kind":"arxiv","id":"2408.06134","version":3},"attestation_state":"computed","paper":{"title":"Learned Indexes with Distribution Smoothing via Virtual Points","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Farhana Choudhury, James Bailey, Jianzhong Qi, Kasun Amarasinghe","submitted_at":"2024-08-12T13:23:49Z","abstract_excerpt":"Recent research on learned indexes has created a new perspective for indexes as models that map keys to their respective storage locations. These learned indexes are created to approximate the cumulative distribution function of the key set, where using only a single model may have limited accuracy. To overcome this limitation, a typical method is to use multiple models, arranged in a hierarchical manner, where the query performance depends on two aspects: (i) traversal time to find the correct model and (ii) search time to find the key in the selected model. Such a method may cause some key s"},"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":"2408.06134","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-12T13:23:49Z","cross_cats_sorted":[],"title_canon_sha256":"40be1656b01d10bc2ffc54db06bf77d74a6c43f163c1b2cad3661ffe2be3ee57","abstract_canon_sha256":"4ccf83d43080c1bdf16e4bb748768d8ff05a8c4bc5b9ff4e3738cd766cce22c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:08.867782Z","signature_b64":"LR7JinKWDp4KtgvZXuqLo5eO5feJJia1M0o0PEQiUKVBhb5qDUUwL7wKZ9Xdrj6l7z0PBcLCKTvmHwZNvHiFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45fa51483b70c7816c4303ff3b3ff6a40f76752cdedcc79a46b721ad60046fe5","last_reissued_at":"2026-07-05T09:49:08.867229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:08.867229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Indexes with Distribution Smoothing via Virtual Points","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Farhana Choudhury, James Bailey, Jianzhong Qi, Kasun Amarasinghe","submitted_at":"2024-08-12T13:23:49Z","abstract_excerpt":"Recent research on learned indexes has created a new perspective for indexes as models that map keys to their respective storage locations. These learned indexes are created to approximate the cumulative distribution function of the key set, where using only a single model may have limited accuracy. To overcome this limitation, a typical method is to use multiple models, arranged in a hierarchical manner, where the query performance depends on two aspects: (i) traversal time to find the correct model and (ii) search time to find the key in the selected model. Such a method may cause some key s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06134","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/2408.06134/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":"2408.06134","created_at":"2026-07-05T09:49:08.867289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06134v3","created_at":"2026-07-05T09:49:08.867289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06134","created_at":"2026-07-05T09:49:08.867289+00:00"},{"alias_kind":"pith_short_12","alias_value":"IX5FCSB3ODDY","created_at":"2026-07-05T09:49:08.867289+00:00"},{"alias_kind":"pith_short_16","alias_value":"IX5FCSB3ODDYC3CD","created_at":"2026-07-05T09:49:08.867289+00:00"},{"alias_kind":"pith_short_8","alias_value":"IX5FCSB3","created_at":"2026-07-05T09:49:08.867289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18003","citing_title":"Self-Balancing, Memory Efficient, Dynamic Metric Space Data Maintenance, for Rapid Multi-Kernel Estimation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ","json":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ.json","graph_json":"https://pith.science/api/pith-number/IX5FCSB3ODDYC3CDAP7TWP7WUQ/graph.json","events_json":"https://pith.science/api/pith-number/IX5FCSB3ODDYC3CDAP7TWP7WUQ/events.json","paper":"https://pith.science/paper/IX5FCSB3"},"agent_actions":{"view_html":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ","download_json":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ.json","view_paper":"https://pith.science/paper/IX5FCSB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06134&json=true","fetch_graph":"https://pith.science/api/pith-number/IX5FCSB3ODDYC3CDAP7TWP7WUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IX5FCSB3ODDYC3CDAP7TWP7WUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ/action/storage_attestation","attest_author":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ/action/author_attestation","sign_citation":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ/action/citation_signature","submit_replication":"https://pith.science/pith/IX5FCSB3ODDYC3CDAP7TWP7WUQ/action/replication_record"}},"created_at":"2026-07-05T09:49:08.867289+00:00","updated_at":"2026-07-05T09:49:08.867289+00:00"}