{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQDOTVR6VXJCAFTRCBUXJIYKA7","short_pith_number":"pith:ZQDOTVR6","schema_version":"1.0","canonical_sha256":"cc06e9d63eadd2201671106974a30a07d22b7100ef09da6bbf3f8b5202de9851","source":{"kind":"arxiv","id":"2507.13892","version":2},"attestation_state":"computed","paper":{"title":"Towards Next Generation Data Engineering Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Kevin M. Kramer, Meike Klettke, Sebastian Strasser, Uta St\\\"orl, Valerie Restat","submitted_at":"2025-07-18T13:12:55Z","abstract_excerpt":"Data engineering pipelines are a widespread way to provide high-quality data for all kinds of data science applications. However, numerous challenges still remain in the composition and operation of such pipelines. Data engineering pipelines do not always deliver high-quality data. By default, they are also not reactive to changes. When new data is coming in which deviates from prior data, the pipeline could crash or output undesired results. We therefore envision three levels of next generation data engineering pipelines: optimized data pipelines, self-aware data pipelines, and self-adapting "},"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":"2507.13892","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T13:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"8b2e03311eb30fac69ba6814e70cba8d0ba45f882de5f50f929ca1f38588e66d","abstract_canon_sha256":"3967bc3c444c08775c0959e658c1d3096ddc2676089ed12e2f0672c64dde7d1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:51.765759Z","signature_b64":"ONrggtZwEfnGkDDStdaA8VdKYZWZjzznaFFVFhZIbJifp09FNTF1jSCIh3KK5Z9DyPH1365g5XmcRRQIX3TKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc06e9d63eadd2201671106974a30a07d22b7100ef09da6bbf3f8b5202de9851","last_reissued_at":"2026-07-05T11:44:51.765323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:51.765323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Next Generation Data Engineering Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Kevin M. Kramer, Meike Klettke, Sebastian Strasser, Uta St\\\"orl, Valerie Restat","submitted_at":"2025-07-18T13:12:55Z","abstract_excerpt":"Data engineering pipelines are a widespread way to provide high-quality data for all kinds of data science applications. However, numerous challenges still remain in the composition and operation of such pipelines. Data engineering pipelines do not always deliver high-quality data. By default, they are also not reactive to changes. When new data is coming in which deviates from prior data, the pipeline could crash or output undesired results. We therefore envision three levels of next generation data engineering pipelines: optimized data pipelines, self-aware data pipelines, and self-adapting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13892","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/2507.13892/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":"2507.13892","created_at":"2026-07-05T11:44:51.765379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13892v2","created_at":"2026-07-05T11:44:51.765379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13892","created_at":"2026-07-05T11:44:51.765379+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQDOTVR6VXJC","created_at":"2026-07-05T11:44:51.765379+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQDOTVR6VXJCAFTR","created_at":"2026-07-05T11:44:51.765379+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQDOTVR6","created_at":"2026-07-05T11:44:51.765379+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/ZQDOTVR6VXJCAFTRCBUXJIYKA7","json":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7.json","graph_json":"https://pith.science/api/pith-number/ZQDOTVR6VXJCAFTRCBUXJIYKA7/graph.json","events_json":"https://pith.science/api/pith-number/ZQDOTVR6VXJCAFTRCBUXJIYKA7/events.json","paper":"https://pith.science/paper/ZQDOTVR6"},"agent_actions":{"view_html":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7","download_json":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7.json","view_paper":"https://pith.science/paper/ZQDOTVR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13892&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQDOTVR6VXJCAFTRCBUXJIYKA7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQDOTVR6VXJCAFTRCBUXJIYKA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7/action/storage_attestation","attest_author":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7/action/author_attestation","sign_citation":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7/action/citation_signature","submit_replication":"https://pith.science/pith/ZQDOTVR6VXJCAFTRCBUXJIYKA7/action/replication_record"}},"created_at":"2026-07-05T11:44:51.765379+00:00","updated_at":"2026-07-05T11:44:51.765379+00:00"}