{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6DGCPKLJVZQK44XUNJKFEYWGUC","short_pith_number":"pith:6DGCPKLJ","schema_version":"1.0","canonical_sha256":"f0cc27a969ae60ae72f46a545262c6a0a2962eaa0a004fe614efd70fc9a4a4db","source":{"kind":"arxiv","id":"2304.08817","version":2},"attestation_state":"computed","paper":{"title":"DILI: A Distribution-Driven Learned Index (Extended version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bolin Ding, Gang Pan, Hua Lu, Long Yang, Pengfei Li, Rong Zhu","submitted_at":"2023-04-18T08:27:24Z","abstract_excerpt":"Targeting in-memory one-dimensional search keys, we propose a novel DIstribution-driven Learned Index tree (DILI), where a concise and computation-efficient linear regression model is used for each node. An internal node's key range is equally divided by its child nodes such that a key search enjoys perfect model prediction accuracy to find the relevant leaf node. A leaf node uses machine learning models to generate searchable data layout and thus accurately predicts the data record position for a key. To construct DILI, we first build a bottom-up tree with linear regression models according t"},"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":"2304.08817","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-04-18T08:27:24Z","cross_cats_sorted":[],"title_canon_sha256":"c364331b31a25eb0bbffc120af79e3c5a4b2bd39aa23b2d38e94265741d4039b","abstract_canon_sha256":"5ab3169061048ceba4b23a69a37636db6db3da9b97b4c7141c1aded2fc1303a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:20.343136Z","signature_b64":"7N2vbnX3fHPERPCwX74ueroGnzP8Vomf61VQf/fJsVl+wQ9+FEk+gWaeGt0PXXLiMrQ3as1ga1+MQ7+6YUrUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0cc27a969ae60ae72f46a545262c6a0a2962eaa0a004fe614efd70fc9a4a4db","last_reissued_at":"2026-07-05T06:11:20.342669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:20.342669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DILI: A Distribution-Driven Learned Index (Extended version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bolin Ding, Gang Pan, Hua Lu, Long Yang, Pengfei Li, Rong Zhu","submitted_at":"2023-04-18T08:27:24Z","abstract_excerpt":"Targeting in-memory one-dimensional search keys, we propose a novel DIstribution-driven Learned Index tree (DILI), where a concise and computation-efficient linear regression model is used for each node. An internal node's key range is equally divided by its child nodes such that a key search enjoys perfect model prediction accuracy to find the relevant leaf node. A leaf node uses machine learning models to generate searchable data layout and thus accurately predicts the data record position for a key. To construct DILI, we first build a bottom-up tree with linear regression models according t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08817","kind":"arxiv","version":2},"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/2304.08817/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":"2304.08817","created_at":"2026-07-05T06:11:20.342729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08817v2","created_at":"2026-07-05T06:11:20.342729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08817","created_at":"2026-07-05T06:11:20.342729+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DGCPKLJVZQK","created_at":"2026-07-05T06:11:20.342729+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DGCPKLJVZQK44XU","created_at":"2026-07-05T06:11:20.342729+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DGCPKLJ","created_at":"2026-07-05T06:11:20.342729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08671","citing_title":"Evaluating Learned Indexes in LSM-tree Systems: Benchmarks,Insights and Design Choices","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC","json":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC.json","graph_json":"https://pith.science/api/pith-number/6DGCPKLJVZQK44XUNJKFEYWGUC/graph.json","events_json":"https://pith.science/api/pith-number/6DGCPKLJVZQK44XUNJKFEYWGUC/events.json","paper":"https://pith.science/paper/6DGCPKLJ"},"agent_actions":{"view_html":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC","download_json":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC.json","view_paper":"https://pith.science/paper/6DGCPKLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08817&json=true","fetch_graph":"https://pith.science/api/pith-number/6DGCPKLJVZQK44XUNJKFEYWGUC/graph.json","fetch_events":"https://pith.science/api/pith-number/6DGCPKLJVZQK44XUNJKFEYWGUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC/action/storage_attestation","attest_author":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC/action/author_attestation","sign_citation":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC/action/citation_signature","submit_replication":"https://pith.science/pith/6DGCPKLJVZQK44XUNJKFEYWGUC/action/replication_record"}},"created_at":"2026-07-05T06:11:20.342729+00:00","updated_at":"2026-07-05T06:11:20.342729+00:00"}