{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XB2RXBEYS3U5FI3CM7OJBDPIAK","short_pith_number":"pith:XB2RXBEY","canonical_record":{"source":{"id":"2606.08266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2026-06-06T17:24:19Z","cross_cats_sorted":[],"title_canon_sha256":"162bd0b0603875c590f63fa19d5ba74b61ec23e020e93be9d72bb7fd41d63490","abstract_canon_sha256":"f7c055c6d58c8b39bba0c8a1be81d9222b0fd67eed9dcf5791a1e87f1e8387c0"},"schema_version":"1.0"},"canonical_sha256":"b8751b849896e9d2a36267dc908de8029b7c2145828a5ec3d8d1a6c6b1671947","source":{"kind":"arxiv","id":"2606.08266","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08266","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08266v1","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08266","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"XB2RXBEYS3U5","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"XB2RXBEYS3U5FI3C","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"XB2RXBEY","created_at":"2026-06-09T01:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XB2RXBEYS3U5FI3CM7OJBDPIAK","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2026-06-06T17:24:19Z","cross_cats_sorted":[],"title_canon_sha256":"162bd0b0603875c590f63fa19d5ba74b61ec23e020e93be9d72bb7fd41d63490","abstract_canon_sha256":"f7c055c6d58c8b39bba0c8a1be81d9222b0fd67eed9dcf5791a1e87f1e8387c0"},"schema_version":"1.0"},"canonical_sha256":"b8751b849896e9d2a36267dc908de8029b7c2145828a5ec3d8d1a6c6b1671947","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:31.785944Z","signature_b64":"V26ns4FJ6HH2c/+N4+acO3ftHyqpcnaSeSi/hcBUpqOmHnfAlF1PDc3aZtBCpLsgFWP0unNpAQC39WdsGE9vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8751b849896e9d2a36267dc908de8029b7c2145828a5ec3d8d1a6c6b1671947","last_reissued_at":"2026-06-09T01:05:31.785531Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:31.785531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08266","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":"2026-06-09T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5+ooWE7csITznvLrvcP+eaeEOFS3kYpWwXAbs9ODZFVuChzf3NqLhrYIYnnPkVkO/EpGduw0VZjqWiX0x4LDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:06:50.784383Z"},"content_sha256":"d0b6320892d42a166e5e6d916372a40e031c664463496728540e020d68fc60fe","schema_version":"1.0","event_id":"sha256:d0b6320892d42a166e5e6d916372a40e031c664463496728540e020d68fc60fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XB2RXBEYS3U5FI3CM7OJBDPIAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Went Wrong with Data Lakes? A 15-Year Reality Check from the Field","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.ET","authors_text":"Youssef Gahi","submitted_at":"2026-06-06T17:24:19Z","abstract_excerpt":"James Dixon introduced the Data Lake in 2010. The pitch was simple: store data raw, postpone schema, cut up-front transformation. It promised flexibility and easier analytics. Fifteen years on, that promise has mostly gone unmet: survey after survey reports high failure rates, whether a big data program, a Data Lake, or a data science effort. This paper asks why. Reading 64 sources across academic work, analyst reports, and practitioner accounts, we found seven recurring anti-patterns, the Seven Deadly Sins of Data Lakes, and offer an explanation for them: Governance Debt, the compounding cost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08266","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/2606.08266/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":"2026-06-09T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DniE0AYQkl6KnPtTEz2v7LwkLyGfX3MgByIobZGHfgv8jDiHfA7v+7lXMw2Pa5yZ1ViPzJUDoflJeClIzTOtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:06:50.784760Z"},"content_sha256":"64eccf819b22b49f5fda6056f8d5e5fca326c39910b20736f70aa5238d7691d8","schema_version":"1.0","event_id":"sha256:64eccf819b22b49f5fda6056f8d5e5fca326c39910b20736f70aa5238d7691d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK/bundle.json","state_url":"https://pith.science/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK/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":"2026-06-30T12:06:50Z","links":{"resolver":"https://pith.science/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK","bundle":"https://pith.science/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK/bundle.json","state":"https://pith.science/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XB2RXBEYS3U5FI3CM7OJBDPIAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XB2RXBEYS3U5FI3CM7OJBDPIAK","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":"f7c055c6d58c8b39bba0c8a1be81d9222b0fd67eed9dcf5791a1e87f1e8387c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2026-06-06T17:24:19Z","title_canon_sha256":"162bd0b0603875c590f63fa19d5ba74b61ec23e020e93be9d72bb7fd41d63490"},"schema_version":"1.0","source":{"id":"2606.08266","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08266","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08266v1","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08266","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"XB2RXBEYS3U5","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"XB2RXBEYS3U5FI3C","created_at":"2026-06-09T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"XB2RXBEY","created_at":"2026-06-09T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:64eccf819b22b49f5fda6056f8d5e5fca326c39910b20736f70aa5238d7691d8","target":"graph","created_at":"2026-06-09T01:05:31Z","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/2606.08266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"James Dixon introduced the Data Lake in 2010. The pitch was simple: store data raw, postpone schema, cut up-front transformation. It promised flexibility and easier analytics. Fifteen years on, that promise has mostly gone unmet: survey after survey reports high failure rates, whether a big data program, a Data Lake, or a data science effort. This paper asks why. Reading 64 sources across academic work, analyst reports, and practitioner accounts, we found seven recurring anti-patterns, the Seven Deadly Sins of Data Lakes, and offer an explanation for them: Governance Debt, the compounding cost","authors_text":"Youssef Gahi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2026-06-06T17:24:19Z","title":"What Went Wrong with Data Lakes? A 15-Year Reality Check from the Field"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08266","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:d0b6320892d42a166e5e6d916372a40e031c664463496728540e020d68fc60fe","target":"record","created_at":"2026-06-09T01:05:31Z","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":"f7c055c6d58c8b39bba0c8a1be81d9222b0fd67eed9dcf5791a1e87f1e8387c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2026-06-06T17:24:19Z","title_canon_sha256":"162bd0b0603875c590f63fa19d5ba74b61ec23e020e93be9d72bb7fd41d63490"},"schema_version":"1.0","source":{"id":"2606.08266","kind":"arxiv","version":1}},"canonical_sha256":"b8751b849896e9d2a36267dc908de8029b7c2145828a5ec3d8d1a6c6b1671947","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8751b849896e9d2a36267dc908de8029b7c2145828a5ec3d8d1a6c6b1671947","first_computed_at":"2026-06-09T01:05:31.785531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:31.785531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V26ns4FJ6HH2c/+N4+acO3ftHyqpcnaSeSi/hcBUpqOmHnfAlF1PDc3aZtBCpLsgFWP0unNpAQC39WdsGE9vDA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:31.785944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08266","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0b6320892d42a166e5e6d916372a40e031c664463496728540e020d68fc60fe","sha256:64eccf819b22b49f5fda6056f8d5e5fca326c39910b20736f70aa5238d7691d8"],"state_sha256":"2b4e958eed4bd5dc8df5e954f88a146d2c3a44b695aef7e28be7ba62c2209640"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kA5ta+4Ry7deQvbPw2pQ32lsKs1pABvTcT0rp5HKtiUOuwC5DTQFgX940akk5qKIWuu7z6O8EIVDoPy+s+d+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T12:06:50.787216Z","bundle_sha256":"833ee583f5897e0ceb49a6383c24de7aef8a3adc97add5a5fc5a960ba83d332c"}}