{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3S7PUINBEDOFNRYBWHUG4K4L5V","short_pith_number":"pith:3S7PUINB","schema_version":"1.0","canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","source":{"kind":"arxiv","id":"1811.09248","version":1},"attestation_state":"computed","paper":{"title":"Data Context Informed Data Wrangling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.DB","authors_text":"Alex Bogatu, Alvaro A. A. Fernandes, Cristina Civili, Edward Abel, John Keane, Leonid Libkin, Martin Koehler, Nikolaos Konstantinou, Norman W. Paton","submitted_at":"2018-11-22T17:34:35Z","abstract_excerpt":"The process of preparing potentially large and complex data sets for further analysis or manual examination is often called data wrangling. In classical warehousing environments, the steps in such a process have been carried out using Extract-Transform-Load platforms, with significant manual involvement in specifying, configuring or tuning many of them. Cost-effective data wrangling processes need to ensure that data wrangling steps benefit from automation wherever possible. In this paper, we define a methodology to fully automate an end-to-end data wrangling process incorporating data context"},"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":"1811.09248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-11-22T17:34:35Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"3f86d045abc8cf286bcd4f882b926f6fd20d99f75575d8cd7ac369f471149e6a","abstract_canon_sha256":"4a8e7d5da083770d48ad1a2af961452e7715498cffd96d3db0cbf5e025c10627"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:03.823752Z","signature_b64":"FDMWtNTuOibI04grKBlu/pvvsRBIYzG7WNT7hydUpueqChsPwmRq6FVoXF3ztwlmITaLcxeCXynH5n6xO+3dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","last_reissued_at":"2026-05-18T00:00:03.823203Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:03.823203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Context Informed Data Wrangling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.DB","authors_text":"Alex Bogatu, Alvaro A. A. Fernandes, Cristina Civili, Edward Abel, John Keane, Leonid Libkin, Martin Koehler, Nikolaos Konstantinou, Norman W. Paton","submitted_at":"2018-11-22T17:34:35Z","abstract_excerpt":"The process of preparing potentially large and complex data sets for further analysis or manual examination is often called data wrangling. In classical warehousing environments, the steps in such a process have been carried out using Extract-Transform-Load platforms, with significant manual involvement in specifying, configuring or tuning many of them. Cost-effective data wrangling processes need to ensure that data wrangling steps benefit from automation wherever possible. In this paper, we define a methodology to fully automate an end-to-end data wrangling process incorporating data context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09248","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":""},"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":"1811.09248","created_at":"2026-05-18T00:00:03.823286+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.09248v1","created_at":"2026-05-18T00:00:03.823286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09248","created_at":"2026-05-18T00:00:03.823286+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S7PUINBEDOF","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S7PUINBEDOFNRYB","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S7PUINB","created_at":"2026-05-18T12:32:05.422762+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/3S7PUINBEDOFNRYBWHUG4K4L5V","json":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V.json","graph_json":"https://pith.science/api/pith-number/3S7PUINBEDOFNRYBWHUG4K4L5V/graph.json","events_json":"https://pith.science/api/pith-number/3S7PUINBEDOFNRYBWHUG4K4L5V/events.json","paper":"https://pith.science/paper/3S7PUINB"},"agent_actions":{"view_html":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V","download_json":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V.json","view_paper":"https://pith.science/paper/3S7PUINB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.09248&json=true","fetch_graph":"https://pith.science/api/pith-number/3S7PUINBEDOFNRYBWHUG4K4L5V/graph.json","fetch_events":"https://pith.science/api/pith-number/3S7PUINBEDOFNRYBWHUG4K4L5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/action/storage_attestation","attest_author":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/action/author_attestation","sign_citation":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/action/citation_signature","submit_replication":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/action/replication_record"}},"created_at":"2026-05-18T00:00:03.823286+00:00","updated_at":"2026-05-18T00:00:03.823286+00:00"}