{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DBUBOCAA5XGUGLLKUNECY3HSYW","short_pith_number":"pith:DBUBOCAA","schema_version":"1.0","canonical_sha256":"1868170800edcd432d6aa3482c6cf2c59e9ec0145a86d7996a2fa08a643f6744","source":{"kind":"arxiv","id":"1903.03676","version":2},"attestation_state":"computed","paper":{"title":"Automated data validation: an industrial experience report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE","stat.AP"],"primary_cat":"cs.DB","authors_text":"Andriy Miranskyy, Jessica Moore, Krittika Mahajan, Lei Zhang, Sean Howard, Tom Montpool","submitted_at":"2019-03-08T21:47:28Z","abstract_excerpt":"There has been a massive explosion of data generated by customers and retained by companies in the last decade. However, there is a significant mismatch between the increasing volume of data and the lack of automation methods and tools. The lack of best practices in data science programming may lead to software quality degradation, release schedule slippage, and budget overruns. To mitigate these concerns, we would like to bring software engineering best practices into data science. Specifically, we focus on automated data validation in the data preparation phase of the software development li"},"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":"1903.03676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-08T21:47:28Z","cross_cats_sorted":["cs.SE","stat.AP"],"title_canon_sha256":"0bf9f0cbf1e74a897ae46ce5d4eaad675463c3838e7c5a203c76b7322a8c7538","abstract_canon_sha256":"2a285c95eb92662d2f8881dc56444de59d2d18eb64c57d9ce1b0cb52181ec51b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:01.490017Z","signature_b64":"xiJ/KXytX+cAbZBrq9G1jROP5OXFBWhIwq5ViOFuwvzLpHf/U/GrIViB2w1caXxHLIKEsjyCZ0u7aagyQCUeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1868170800edcd432d6aa3482c6cf2c59e9ec0145a86d7996a2fa08a643f6744","last_reissued_at":"2026-07-05T05:22:01.489582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:01.489582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated data validation: an industrial experience report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE","stat.AP"],"primary_cat":"cs.DB","authors_text":"Andriy Miranskyy, Jessica Moore, Krittika Mahajan, Lei Zhang, Sean Howard, Tom Montpool","submitted_at":"2019-03-08T21:47:28Z","abstract_excerpt":"There has been a massive explosion of data generated by customers and retained by companies in the last decade. However, there is a significant mismatch between the increasing volume of data and the lack of automation methods and tools. The lack of best practices in data science programming may lead to software quality degradation, release schedule slippage, and budget overruns. To mitigate these concerns, we would like to bring software engineering best practices into data science. Specifically, we focus on automated data validation in the data preparation phase of the software development li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03676","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/1903.03676/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":"1903.03676","created_at":"2026-07-05T05:22:01.489638+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03676v2","created_at":"2026-07-05T05:22:01.489638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03676","created_at":"2026-07-05T05:22:01.489638+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBUBOCAA5XGU","created_at":"2026-07-05T05:22:01.489638+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBUBOCAA5XGUGLLK","created_at":"2026-07-05T05:22:01.489638+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBUBOCAA","created_at":"2026-07-05T05:22:01.489638+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/DBUBOCAA5XGUGLLKUNECY3HSYW","json":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW.json","graph_json":"https://pith.science/api/pith-number/DBUBOCAA5XGUGLLKUNECY3HSYW/graph.json","events_json":"https://pith.science/api/pith-number/DBUBOCAA5XGUGLLKUNECY3HSYW/events.json","paper":"https://pith.science/paper/DBUBOCAA"},"agent_actions":{"view_html":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW","download_json":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW.json","view_paper":"https://pith.science/paper/DBUBOCAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03676&json=true","fetch_graph":"https://pith.science/api/pith-number/DBUBOCAA5XGUGLLKUNECY3HSYW/graph.json","fetch_events":"https://pith.science/api/pith-number/DBUBOCAA5XGUGLLKUNECY3HSYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW/action/storage_attestation","attest_author":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW/action/author_attestation","sign_citation":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW/action/citation_signature","submit_replication":"https://pith.science/pith/DBUBOCAA5XGUGLLKUNECY3HSYW/action/replication_record"}},"created_at":"2026-07-05T05:22:01.489638+00:00","updated_at":"2026-07-05T05:22:01.489638+00:00"}