{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YXARMHBHD5ISUIHWDOJM2MFPS4","short_pith_number":"pith:YXARMHBH","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"},"canonical_sha256":"c5c1161c271f512a20f61b92cd30af9704f965825e60acd591b779498b320237","source":{"kind":"arxiv","id":"2504.04186","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04186","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04186v1","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04186","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"YXARMHBHD5IS","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"YXARMHBHD5ISUIHW","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"YXARMHBH","created_at":"2026-07-05T10:44:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YXARMHBHD5ISUIHWDOJM2MFPS4","target":"record","payload":{"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"},"canonical_sha256":"c5c1161c271f512a20f61b92cd30af9704f965825e60acd591b779498b320237","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"},"source_kind":"arxiv","source_id":"2504.04186","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBzq7hoHMVbU7hW2q3saZBgObPyfhWcTWLdWRZDmErHhAQoT/qtJJM+CuS+MTCtQe8IzKV3d9Jh5yQQl8NzDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:48:33.027729Z"},"content_sha256":"63e7c6520fcb78914b0c22824985f257d59ff1a022206055942ca29c3654de66","schema_version":"1.0","event_id":"sha256:63e7c6520fcb78914b0c22824985f257d59ff1a022206055942ca29c3654de66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YXARMHBHD5ISUIHWDOJM2MFPS4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrGHhqtpZzyOTU1kcEZWsoHr9VSX4ZT25jHzwxFP0QGDRB5qlOvG6Hfmq8zl/hO0BmFHVE3jhgrgY4hp7zN6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:48:33.028118Z"},"content_sha256":"541c9fc1cd5a2364106ff4409679f153a114d924be389ca6d8ae970fc3bee359","schema_version":"1.0","event_id":"sha256:541c9fc1cd5a2364106ff4409679f153a114d924be389ca6d8ae970fc3bee359"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/bundle.json","state_url":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T14:48:33Z","links":{"resolver":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4","bundle":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/bundle.json","state":"https://pith.science/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YXARMHBHD5ISUIHWDOJM2MFPS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YXARMHBHD5ISUIHWDOJM2MFPS4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3ac7f8d393ebb99283e5f46390bd51c20472de4cc808bca8f4800e7995c1ffd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-05T14:10:58Z","title_canon_sha256":"8c9251dae23302281d0540182c46aaa98b64873c4c07f21ad3deba92f449bf95"},"schema_version":"1.0","source":{"id":"2504.04186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04186","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04186v1","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04186","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"YXARMHBHD5IS","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"YXARMHBHD5ISUIHW","created_at":"2026-07-05T10:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"YXARMHBH","created_at":"2026-07-05T10:44:55Z"}],"graph_snapshots":[{"event_id":"sha256:541c9fc1cd5a2364106ff4409679f153a114d924be389ca6d8ae970fc3bee359","target":"graph","created_at":"2026-07-05T10:44:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.04186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-05T14:10:58Z","title":"AutoComp: Automated Data Compaction for Log-Structured Tables in Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04186","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:63e7c6520fcb78914b0c22824985f257d59ff1a022206055942ca29c3654de66","target":"record","created_at":"2026-07-05T10:44:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3ac7f8d393ebb99283e5f46390bd51c20472de4cc808bca8f4800e7995c1ffd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-05T14:10:58Z","title_canon_sha256":"8c9251dae23302281d0540182c46aaa98b64873c4c07f21ad3deba92f449bf95"},"schema_version":"1.0","source":{"id":"2504.04186","kind":"arxiv","version":1}},"canonical_sha256":"c5c1161c271f512a20f61b92cd30af9704f965825e60acd591b779498b320237","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5c1161c271f512a20f61b92cd30af9704f965825e60acd591b779498b320237","first_computed_at":"2026-07-05T10:44:55.410102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:55.410102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46ehzlFHCZdnEN0lXlYEVE/980vAF+hHcFJXZuNrcQsL0MIurFX/3nBbtOA74MPR0wItuiiviQyJX1wVU+/uDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:55.410510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63e7c6520fcb78914b0c22824985f257d59ff1a022206055942ca29c3654de66","sha256:541c9fc1cd5a2364106ff4409679f153a114d924be389ca6d8ae970fc3bee359"],"state_sha256":"d31ad73626bce37a49efbf7f750a3aec0466b7175daa81b33bb45e0079a00523"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+doAFczvHRoH0+3bEJV4hh1VU39waTH/iRjIxvMpCkQ2JAn5Jh7ArOQkFaESkggE5F0V+qkTLFntKALRBPjZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T14:48:33.030203Z","bundle_sha256":"1c403b719927ca995831f37894f6195ba8d0a5ecc0052256d2889cb2f9fb48f4"}}