{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YXARMHBHD5ISUIHWDOJM2MFPS4","short_pith_number":"pith:YXARMHBH","schema_version":"1.0","canonical_sha256":"c5c1161c271f512a20f61b92cd30af9704f965825e60acd591b779498b320237","source":{"kind":"arxiv","id":"2504.04186","version":1},"attestation_state":"computed","paper":{"title":"AutoComp: Automated Data Compaction for Log-Structured Tables in Data Lakes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anja Gruenheid, Carlo Curino, Daniel J. Abadi, Jes\\'us Camacho-Rodr\\'iguez, Lenisha Gandhi, Pooja Nilangekar, Raghu Ramakrishnan, Sandeep K. Singhal, Stanislav Pak, Sumedh Sakdeo","submitted_at":"2025-04-05T14:10:58Z","abstract_excerpt":"The proliferation of small files in data lakes poses significant challenges, including degraded query performance, increased storage costs, and scalability bottlenecks in distributed storage systems. Log-structured table formats (LSTs) such as Delta Lake, Apache Iceberg, and Apache Hudi exacerbate this issue due to their append-only write patterns and metadata-intensive operations. While compaction--the process of consolidating small files into fewer, larger files--is a common solution, existing automation mechanisms often lack the flexibility and scalability to adapt to diverse workloads and "},"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":"2504.04186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-05T14:10:58Z","cross_cats_sorted":[],"title_canon_sha256":"8c9251dae23302281d0540182c46aaa98b64873c4c07f21ad3deba92f449bf95","abstract_canon_sha256":"3ac7f8d393ebb99283e5f46390bd51c20472de4cc808bca8f4800e7995c1ffd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:55.410510Z","signature_b64":"46ehzlFHCZdnEN0lXlYEVE/980vAF+hHcFJXZuNrcQsL0MIurFX/3nBbtOA74MPR0wItuiiviQyJX1wVU+/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5c1161c271f512a20f61b92cd30af9704f965825e60acd591b779498b320237","last_reissued_at":"2026-07-05T10:44:55.410102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:55.410102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoComp: Automated Data Compaction for Log-Structured Tables in Data Lakes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anja Gruenheid, Carlo Curino, Daniel J. Abadi, Jes\\'us Camacho-Rodr\\'iguez, Lenisha Gandhi, Pooja Nilangekar, Raghu Ramakrishnan, Sandeep K. Singhal, Stanislav Pak, Sumedh Sakdeo","submitted_at":"2025-04-05T14:10:58Z","abstract_excerpt":"The proliferation of small files in data lakes poses significant challenges, including degraded query performance, increased storage costs, and scalability bottlenecks in distributed storage systems. Log-structured table formats (LSTs) such as Delta Lake, Apache Iceberg, and Apache Hudi exacerbate this issue due to their append-only write patterns and metadata-intensive operations. While compaction--the process of consolidating small files into fewer, larger files--is a common solution, existing automation mechanisms often lack the flexibility and scalability to adapt to diverse workloads and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04186","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/2504.04186/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":"2504.04186","created_at":"2026-07-05T10:44:55.410159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04186v1","created_at":"2026-07-05T10:44:55.410159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04186","created_at":"2026-07-05T10:44:55.410159+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXARMHBHD5IS","created_at":"2026-07-05T10:44:55.410159+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXARMHBHD5ISUIHW","created_at":"2026-07-05T10:44:55.410159+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXARMHBH","created_at":"2026-07-05T10:44:55.410159+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/YXARMHBHD5ISUIHWDOJM2MFPS4","json":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4.json","graph_json":"https://pith.science/api/pith-number/YXARMHBHD5ISUIHWDOJM2MFPS4/graph.json","events_json":"https://pith.science/api/pith-number/YXARMHBHD5ISUIHWDOJM2MFPS4/events.json","paper":"https://pith.science/paper/YXARMHBH"},"agent_actions":{"view_html":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4","download_json":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4.json","view_paper":"https://pith.science/paper/YXARMHBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04186&json=true","fetch_graph":"https://pith.science/api/pith-number/YXARMHBHD5ISUIHWDOJM2MFPS4/graph.json","fetch_events":"https://pith.science/api/pith-number/YXARMHBHD5ISUIHWDOJM2MFPS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/action/storage_attestation","attest_author":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/action/author_attestation","sign_citation":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/action/citation_signature","submit_replication":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/action/replication_record"}},"created_at":"2026-07-05T10:44:55.410159+00:00","updated_at":"2026-07-05T10:44:55.410159+00:00"}