{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IDCVGEMSCLRBUOAJRE3TJCVDRI","short_pith_number":"pith:IDCVGEMS","canonical_record":{"source":{"id":"2602.10441","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:33:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"819721093eac8fc314a3ef76b32bc54b868cd1d3411268a1d032562eb6baaca9","abstract_canon_sha256":"901e5f181a89856b7faad00278e2ae8e3a544d1191ef99e0c1254cb16bafff09"},"schema_version":"1.0"},"canonical_sha256":"40c553119212e21a38098937348aa38a21f68b273503d2605c46b9c0ca900323","source":{"kind":"arxiv","id":"2602.10441","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.10441","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"arxiv_version","alias_value":"2602.10441v2","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10441","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"pith_short_12","alias_value":"IDCVGEMSCLRB","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"pith_short_16","alias_value":"IDCVGEMSCLRBUOAJ","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"pith_short_8","alias_value":"IDCVGEMS","created_at":"2026-08-04T02:09:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IDCVGEMSCLRBUOAJRE3TJCVDRI","target":"record","payload":{"canonical_record":{"source":{"id":"2602.10441","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:33:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"819721093eac8fc314a3ef76b32bc54b868cd1d3411268a1d032562eb6baaca9","abstract_canon_sha256":"901e5f181a89856b7faad00278e2ae8e3a544d1191ef99e0c1254cb16bafff09"},"schema_version":"1.0"},"canonical_sha256":"40c553119212e21a38098937348aa38a21f68b273503d2605c46b9c0ca900323","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:09:21.420504Z","signature_b64":"TThNwfmV5Ua3z30DjB9BMQD/EoCYLLdnfA71AKPAs0xX2BK9RtMiUniizQpl4DIIOzZnMljLuC4uUQ7DayNcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40c553119212e21a38098937348aa38a21f68b273503d2605c46b9c0ca900323","last_reissued_at":"2026-08-04T02:09:21.418788Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:09:21.418788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.10441","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T02:09:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/MlEcD+49Q8Lgbg0US3MBSNAaiYD7hNAGkI/XD81pv71hS5dk0Mlip74LakVR91gc6wa3o8SCySuu5DK5gZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:30:38.090888Z"},"content_sha256":"f46e22df367dd03aebfff8eae4412ac3de60ffb3a31b48384680866ff9c2160d","schema_version":"1.0","event_id":"sha256:f46e22df367dd03aebfff8eae4412ac3de60ffb3a31b48384680866ff9c2160d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IDCVGEMSCLRBUOAJRE3TJCVDRI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LakeMLB: Data Lake Machine Learning Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aoqian Zhang, Feiyu Pan, Jianhua Li, Li Pan, Lixing Chen, Tianbin Zhang, Yu Sun, Zheng Wang","submitted_at":"2026-02-11T02:33:29Z","abstract_excerpt":"Data lakes have become a fundamental platform for large-scale machine learning by enabling flexible management of heterogeneous data. Despite their growing importance, standardized benchmarks for evaluating machine learning performance in data lake environments remain scarce. To address this gap, we present LakeMLB (Data Lake Machine Learning Benchmark), the first benchmark designed for multi-table machine learning in data lakes. LakeMLB focuses on two representative scenarios, Union and Join, and provides six real-world datasets spanning diverse domains. It supports three representative multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10441","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/2602.10441/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":"2026-08-04T02:09:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVowDbMuN52kaLsPuv5XbipNAbWKCealMgEv7W1Dw+xV4Jb5RBNiwXlbPSHivFs2wTGv6jefpRnJ56Q256dQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:30:38.091420Z"},"content_sha256":"6218cfe3bdcb7efeb40f26d56f4016644e5332f6bc3090412c9af43370b7c6cf","schema_version":"1.0","event_id":"sha256:6218cfe3bdcb7efeb40f26d56f4016644e5332f6bc3090412c9af43370b7c6cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI/bundle.json","state_url":"https://pith.science/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI/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":"2026-08-06T10:30:38Z","links":{"resolver":"https://pith.science/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI","bundle":"https://pith.science/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI/bundle.json","state":"https://pith.science/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDCVGEMSCLRBUOAJRE3TJCVDRI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IDCVGEMSCLRBUOAJRE3TJCVDRI","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":"901e5f181a89856b7faad00278e2ae8e3a544d1191ef99e0c1254cb16bafff09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:33:29Z","title_canon_sha256":"819721093eac8fc314a3ef76b32bc54b868cd1d3411268a1d032562eb6baaca9"},"schema_version":"1.0","source":{"id":"2602.10441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.10441","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"arxiv_version","alias_value":"2602.10441v2","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10441","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"pith_short_12","alias_value":"IDCVGEMSCLRB","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"pith_short_16","alias_value":"IDCVGEMSCLRBUOAJ","created_at":"2026-08-04T02:09:21Z"},{"alias_kind":"pith_short_8","alias_value":"IDCVGEMS","created_at":"2026-08-04T02:09:21Z"}],"graph_snapshots":[{"event_id":"sha256:6218cfe3bdcb7efeb40f26d56f4016644e5332f6bc3090412c9af43370b7c6cf","target":"graph","created_at":"2026-08-04T02:09:21Z","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/2602.10441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data lakes have become a fundamental platform for large-scale machine learning by enabling flexible management of heterogeneous data. Despite their growing importance, standardized benchmarks for evaluating machine learning performance in data lake environments remain scarce. To address this gap, we present LakeMLB (Data Lake Machine Learning Benchmark), the first benchmark designed for multi-table machine learning in data lakes. LakeMLB focuses on two representative scenarios, Union and Join, and provides six real-world datasets spanning diverse domains. It supports three representative multi","authors_text":"Aoqian Zhang, Feiyu Pan, Jianhua Li, Li Pan, Lixing Chen, Tianbin Zhang, Yu Sun, Zheng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:33:29Z","title":"LakeMLB: Data Lake Machine Learning Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10441","kind":"arxiv","version":2},"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:f46e22df367dd03aebfff8eae4412ac3de60ffb3a31b48384680866ff9c2160d","target":"record","created_at":"2026-08-04T02:09:21Z","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":"901e5f181a89856b7faad00278e2ae8e3a544d1191ef99e0c1254cb16bafff09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:33:29Z","title_canon_sha256":"819721093eac8fc314a3ef76b32bc54b868cd1d3411268a1d032562eb6baaca9"},"schema_version":"1.0","source":{"id":"2602.10441","kind":"arxiv","version":2}},"canonical_sha256":"40c553119212e21a38098937348aa38a21f68b273503d2605c46b9c0ca900323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40c553119212e21a38098937348aa38a21f68b273503d2605c46b9c0ca900323","first_computed_at":"2026-08-04T02:09:21.418788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:09:21.418788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TThNwfmV5Ua3z30DjB9BMQD/EoCYLLdnfA71AKPAs0xX2BK9RtMiUniizQpl4DIIOzZnMljLuC4uUQ7DayNcDA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:09:21.420504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.10441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f46e22df367dd03aebfff8eae4412ac3de60ffb3a31b48384680866ff9c2160d","sha256:6218cfe3bdcb7efeb40f26d56f4016644e5332f6bc3090412c9af43370b7c6cf"],"state_sha256":"efd34509dcb74ae6782cd6686f8e666b12e7f88d94c0b14bc8ddb0fabe4e581a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBsQz8kTw+rWO/upPwJuaJPkKaRWVRIorwmY7IpeY1PmyNzbYYE78KpuBrvdW0EQvBoxmXu83ZBQEpi7P+JFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:30:38.097144Z","bundle_sha256":"f57aba6ac9111bf59fb479594cad27c69f034adcd7de36530b673429873ebb6b"}}