{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3ROKOVLFRH3GYPJKKXDIZGWGFX","short_pith_number":"pith:3ROKOVLF","schema_version":"1.0","canonical_sha256":"dc5ca7556589f66c3d2a55c68c9ac62dee9c65b35911c0bc2235e5b7fdf609a5","source":{"kind":"arxiv","id":"2004.12929","version":1},"attestation_state":"computed","paper":{"title":"Data Engineering for Data Analytics: A Classification of the Issues, and Case Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alfredo Nazabal, Angus Williams, Camila Rangel Smith, Christopher K.I. Williams, Giovanni Colavizza","submitted_at":"2020-04-27T16:42:40Z","abstract_excerpt":"Consider the situation where a data analyst wishes to carry out an analysis on a given dataset. It is widely recognized that most of the analyst's time will be taken up with \\emph{data engineering} tasks such as acquiring, understanding, cleaning and preparing the data. In this paper we provide a description and classification of such tasks into high-levels groups, namely data organization, data quality and feature engineering. We also make available four datasets and example analyses that exhibit a wide variety of these problems, to help encourage the development of tools and techniques to he"},"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":"2004.12929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-27T16:42:40Z","cross_cats_sorted":[],"title_canon_sha256":"ae4f6849f7dbf34109293e285b9c45673d53892a24117a07f593475ccb2513c7","abstract_canon_sha256":"e074d9dbe450d11cfdb301535df9732224c571e0bb46c794d0c31411a2352ecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:28.710389Z","signature_b64":"w8h1yPNes5DG7v2NMd1rh0i1fxR1VuofPoraDBWC68BwJc7X1ry8iksMjUCu24Vl+wbM55JTsJpRBeOqoywKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc5ca7556589f66c3d2a55c68c9ac62dee9c65b35911c0bc2235e5b7fdf609a5","last_reissued_at":"2026-07-05T00:58:28.709873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:28.709873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Engineering for Data Analytics: A Classification of the Issues, and Case Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alfredo Nazabal, Angus Williams, Camila Rangel Smith, Christopher K.I. Williams, Giovanni Colavizza","submitted_at":"2020-04-27T16:42:40Z","abstract_excerpt":"Consider the situation where a data analyst wishes to carry out an analysis on a given dataset. It is widely recognized that most of the analyst's time will be taken up with \\emph{data engineering} tasks such as acquiring, understanding, cleaning and preparing the data. In this paper we provide a description and classification of such tasks into high-levels groups, namely data organization, data quality and feature engineering. We also make available four datasets and example analyses that exhibit a wide variety of these problems, to help encourage the development of tools and techniques to he"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12929","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/2004.12929/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":"2004.12929","created_at":"2026-07-05T00:58:28.709943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12929v1","created_at":"2026-07-05T00:58:28.709943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12929","created_at":"2026-07-05T00:58:28.709943+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ROKOVLFRH3G","created_at":"2026-07-05T00:58:28.709943+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ROKOVLFRH3GYPJK","created_at":"2026-07-05T00:58:28.709943+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ROKOVLF","created_at":"2026-07-05T00:58:28.709943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23118","citing_title":"FlowETL: An Autonomous Example-Driven Pipeline for Data Engineering","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX","json":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX.json","graph_json":"https://pith.science/api/pith-number/3ROKOVLFRH3GYPJKKXDIZGWGFX/graph.json","events_json":"https://pith.science/api/pith-number/3ROKOVLFRH3GYPJKKXDIZGWGFX/events.json","paper":"https://pith.science/paper/3ROKOVLF"},"agent_actions":{"view_html":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX","download_json":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX.json","view_paper":"https://pith.science/paper/3ROKOVLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12929&json=true","fetch_graph":"https://pith.science/api/pith-number/3ROKOVLFRH3GYPJKKXDIZGWGFX/graph.json","fetch_events":"https://pith.science/api/pith-number/3ROKOVLFRH3GYPJKKXDIZGWGFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX/action/storage_attestation","attest_author":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX/action/author_attestation","sign_citation":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX/action/citation_signature","submit_replication":"https://pith.science/pith/3ROKOVLFRH3GYPJKKXDIZGWGFX/action/replication_record"}},"created_at":"2026-07-05T00:58:28.709943+00:00","updated_at":"2026-07-05T00:58:28.709943+00:00"}