{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZAWTPUPWCTPJ44OFLJVP4EC4HH","short_pith_number":"pith:ZAWTPUPW","schema_version":"1.0","canonical_sha256":"c82d37d1f614de9e71c55a6afe105c39d937ac1760cb71a0bc3fd25f846f3fab","source":{"kind":"arxiv","id":"2508.00882","version":1},"attestation_state":"computed","paper":{"title":"Learned LSM-trees: Two Approaches Using Learned Bloom Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Nicholas Fidalgo, Puyuan Ye","submitted_at":"2025-07-24T04:23:52Z","abstract_excerpt":"Modern key-value stores rely heavily on Log-Structured Merge (LSM) trees for write optimization, but this design introduces significant read amplification. Auxiliary structures like Bloom filters help, but impose memory costs that scale with tree depth and dataset size. Recent advances in learned data structures suggest that machine learning models can augment or replace these components, trading handcrafted heuristics for data-adaptive behavior. In this work, we explore two approaches for integrating learned predictions into the LSM-tree lookup path. The first uses a classifier to selectively"},"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":"2508.00882","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2025-07-24T04:23:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c9e3e42eb2207d985008e72b3d288bec95273f3bbaa5c4ca3a9c6db5990f2e0b","abstract_canon_sha256":"6a38592f0899596f434395d779b935aaaad283d9f532116ead04a027e6c679db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:29.147404Z","signature_b64":"mS3RHs02qWIjAmpcispdVVWgdHcm6ljz3ljfUbVf9twh7SL4VFe8ROJpfvvqgW5HhxgDprMK0HhWhb+XQ5b9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c82d37d1f614de9e71c55a6afe105c39d937ac1760cb71a0bc3fd25f846f3fab","last_reissued_at":"2026-07-05T11:47:29.146986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:29.146986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned LSM-trees: Two Approaches Using Learned Bloom Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Nicholas Fidalgo, Puyuan Ye","submitted_at":"2025-07-24T04:23:52Z","abstract_excerpt":"Modern key-value stores rely heavily on Log-Structured Merge (LSM) trees for write optimization, but this design introduces significant read amplification. Auxiliary structures like Bloom filters help, but impose memory costs that scale with tree depth and dataset size. Recent advances in learned data structures suggest that machine learning models can augment or replace these components, trading handcrafted heuristics for data-adaptive behavior. In this work, we explore two approaches for integrating learned predictions into the LSM-tree lookup path. The first uses a classifier to selectively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00882","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/2508.00882/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":"2508.00882","created_at":"2026-07-05T11:47:29.147049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00882v1","created_at":"2026-07-05T11:47:29.147049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00882","created_at":"2026-07-05T11:47:29.147049+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAWTPUPWCTPJ","created_at":"2026-07-05T11:47:29.147049+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAWTPUPWCTPJ44OF","created_at":"2026-07-05T11:47:29.147049+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAWTPUPW","created_at":"2026-07-05T11:47:29.147049+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/ZAWTPUPWCTPJ44OFLJVP4EC4HH","json":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH.json","graph_json":"https://pith.science/api/pith-number/ZAWTPUPWCTPJ44OFLJVP4EC4HH/graph.json","events_json":"https://pith.science/api/pith-number/ZAWTPUPWCTPJ44OFLJVP4EC4HH/events.json","paper":"https://pith.science/paper/ZAWTPUPW"},"agent_actions":{"view_html":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH","download_json":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH.json","view_paper":"https://pith.science/paper/ZAWTPUPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00882&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAWTPUPWCTPJ44OFLJVP4EC4HH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAWTPUPWCTPJ44OFLJVP4EC4HH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH/action/storage_attestation","attest_author":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH/action/author_attestation","sign_citation":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH/action/citation_signature","submit_replication":"https://pith.science/pith/ZAWTPUPWCTPJ44OFLJVP4EC4HH/action/replication_record"}},"created_at":"2026-07-05T11:47:29.147049+00:00","updated_at":"2026-07-05T11:47:29.147049+00:00"}