{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G7HXKV65CFIMJW2QNCRORRYL7V","short_pith_number":"pith:G7HXKV65","schema_version":"1.0","canonical_sha256":"37cf7557dd1150c4db5068a2e8c70bfd7d01d929d8ce13af855bb5c9a30aeab8","source":{"kind":"arxiv","id":"2308.07013","version":2},"attestation_state":"computed","paper":{"title":"Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Caihua Shan, Dingheng Mo, Fanchao Chen, Siqiang Luo","submitted_at":"2023-08-14T09:00:58Z","abstract_excerpt":"LSM-trees are widely adopted as the storage backend of key-value stores. However, optimizing the system performance under dynamic workloads has not been sufficiently studied or evaluated in previous work. To fill the gap, we present RusKey, a key-value store with the following new features: (1) RusKey is a first attempt to orchestrate LSM-tree structures online to enable robust performance under the context of dynamic workloads; (2) RusKey is the first study to use Reinforcement Learning (RL) to guide LSM-tree transformations; (3) RusKey includes a new LSM-tree design, named FLSM-tree, for an "},"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":"2308.07013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-08-14T09:00:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee37f1e783245850a8abed4e091f971adbb7e31c347222fb9c8f9be454b8aa92","abstract_canon_sha256":"7f6aac86f21f54efd4ae2396c6f16a8612572780223625352b8da5245a74dfdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:28.200244Z","signature_b64":"ukpuftvhw6BG2uEMGQvBeO2L6P563Jt7PUu7qNOouaM0iXRDIJmyDhLCxStdO6K5sq0I74U0iWf6QEjUV/oKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37cf7557dd1150c4db5068a2e8c70bfd7d01d929d8ce13af855bb5c9a30aeab8","last_reissued_at":"2026-07-05T06:51:28.199762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:28.199762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Caihua Shan, Dingheng Mo, Fanchao Chen, Siqiang Luo","submitted_at":"2023-08-14T09:00:58Z","abstract_excerpt":"LSM-trees are widely adopted as the storage backend of key-value stores. However, optimizing the system performance under dynamic workloads has not been sufficiently studied or evaluated in previous work. To fill the gap, we present RusKey, a key-value store with the following new features: (1) RusKey is a first attempt to orchestrate LSM-tree structures online to enable robust performance under the context of dynamic workloads; (2) RusKey is the first study to use Reinforcement Learning (RL) to guide LSM-tree transformations; (3) RusKey includes a new LSM-tree design, named FLSM-tree, for an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07013","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/2308.07013/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":"2308.07013","created_at":"2026-07-05T06:51:28.199818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07013v2","created_at":"2026-07-05T06:51:28.199818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07013","created_at":"2026-07-05T06:51:28.199818+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7HXKV65CFIM","created_at":"2026-07-05T06:51:28.199818+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7HXKV65CFIMJW2Q","created_at":"2026-07-05T06:51:28.199818+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7HXKV65","created_at":"2026-07-05T06:51:28.199818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05001","citing_title":"A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V","json":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V.json","graph_json":"https://pith.science/api/pith-number/G7HXKV65CFIMJW2QNCRORRYL7V/graph.json","events_json":"https://pith.science/api/pith-number/G7HXKV65CFIMJW2QNCRORRYL7V/events.json","paper":"https://pith.science/paper/G7HXKV65"},"agent_actions":{"view_html":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V","download_json":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V.json","view_paper":"https://pith.science/paper/G7HXKV65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07013&json=true","fetch_graph":"https://pith.science/api/pith-number/G7HXKV65CFIMJW2QNCRORRYL7V/graph.json","fetch_events":"https://pith.science/api/pith-number/G7HXKV65CFIMJW2QNCRORRYL7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V/action/storage_attestation","attest_author":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V/action/author_attestation","sign_citation":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V/action/citation_signature","submit_replication":"https://pith.science/pith/G7HXKV65CFIMJW2QNCRORRYL7V/action/replication_record"}},"created_at":"2026-07-05T06:51:28.199818+00:00","updated_at":"2026-07-05T06:51:28.199818+00:00"}