{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3ROKOVLFRH3GYPJKKXDIZGWGFX","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":"e074d9dbe450d11cfdb301535df9732224c571e0bb46c794d0c31411a2352ecc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-27T16:42:40Z","title_canon_sha256":"ae4f6849f7dbf34109293e285b9c45673d53892a24117a07f593475ccb2513c7"},"schema_version":"1.0","source":{"id":"2004.12929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12929","created_at":"2026-07-05T00:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12929v1","created_at":"2026-07-05T00:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12929","created_at":"2026-07-05T00:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"3ROKOVLFRH3G","created_at":"2026-07-05T00:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"3ROKOVLFRH3GYPJK","created_at":"2026-07-05T00:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"3ROKOVLF","created_at":"2026-07-05T00:58:28Z"}],"graph_snapshots":[{"event_id":"sha256:a93b0c83f7d7b69092ee85002aad3384eeb8e7116accf7e563e5a84614db2e89","target":"graph","created_at":"2026-07-05T00:58:28Z","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/2004.12929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alfredo Nazabal, Angus Williams, Camila Rangel Smith, Christopher K.I. Williams, Giovanni Colavizza","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-27T16:42:40Z","title":"Data Engineering for Data Analytics: A Classification of the Issues, and Case Studies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12929","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:a38381bc57b440da46db7109589cde33131b13188a056c3706c104d10c6d360b","target":"record","created_at":"2026-07-05T00:58:28Z","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":"e074d9dbe450d11cfdb301535df9732224c571e0bb46c794d0c31411a2352ecc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-27T16:42:40Z","title_canon_sha256":"ae4f6849f7dbf34109293e285b9c45673d53892a24117a07f593475ccb2513c7"},"schema_version":"1.0","source":{"id":"2004.12929","kind":"arxiv","version":1}},"canonical_sha256":"dc5ca7556589f66c3d2a55c68c9ac62dee9c65b35911c0bc2235e5b7fdf609a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc5ca7556589f66c3d2a55c68c9ac62dee9c65b35911c0bc2235e5b7fdf609a5","first_computed_at":"2026-07-05T00:58:28.709873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:28.709873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w8h1yPNes5DG7v2NMd1rh0i1fxR1VuofPoraDBWC68BwJc7X1ry8iksMjUCu24Vl+wbM55JTsJpRBeOqoywKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:28.710389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.12929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a38381bc57b440da46db7109589cde33131b13188a056c3706c104d10c6d360b","sha256:a93b0c83f7d7b69092ee85002aad3384eeb8e7116accf7e563e5a84614db2e89"],"state_sha256":"8e9e69ef5313eb80b4827e1962f2c0d4ce4f5eb9d2e08bcd03b148866bea0571"}