{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6O7ZBZXODJAU5TLD3D6USCCCZ5","short_pith_number":"pith:6O7ZBZXO","schema_version":"1.0","canonical_sha256":"f3bf90e6ee1a414ecd63d8fd490842cf485af434fdb27af56f12a5e44b929991","source":{"kind":"arxiv","id":"2004.04139","version":1},"attestation_state":"computed","paper":{"title":"Fast and Reliable Missing Data Contingency Analysis with Predicate-Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aaron J. Elmore, Michael J. Franklin, Sanjay Krishnan, Xi Liang, Zechao Shang","submitted_at":"2020-04-08T17:50:18Z","abstract_excerpt":"Today, data analysts largely rely on intuition to determine whether missing or withheld rows of a dataset significantly affect their analyses. We propose a framework that can produce automatic contingency analysis, i.e., the range of values an aggregate SQL query could take, under formal constraints describing the variation and frequency of missing data tuples. We describe how to process SUM, COUNT, AVG, MIN, and MAX queries in these conditions resulting in hard error bounds with testable constraints. We propose an optimization algorithm based on an integer program that reconciles a set of suc"},"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":"2004.04139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-08T17:50:18Z","cross_cats_sorted":[],"title_canon_sha256":"389312f3ef431a2327f14d87f28a230b4a24560a64d5ee1836aafa2716628153","abstract_canon_sha256":"0d622bb139ee50ab54205331eb8dfb77014c5ff48f54bed68fc09ceb2f7d8fbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:59.317403Z","signature_b64":"2aYpRPC1kdS/QVigJx3wNfbVQfGjQ/ngfD6R2JybvNA44Rc1OMz4jpmxDSMACB8g1v7MmAGbwgZaNpN6e3zEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3bf90e6ee1a414ecd63d8fd490842cf485af434fdb27af56f12a5e44b929991","last_reissued_at":"2026-07-05T00:53:59.316958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:59.316958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Reliable Missing Data Contingency Analysis with Predicate-Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aaron J. Elmore, Michael J. Franklin, Sanjay Krishnan, Xi Liang, Zechao Shang","submitted_at":"2020-04-08T17:50:18Z","abstract_excerpt":"Today, data analysts largely rely on intuition to determine whether missing or withheld rows of a dataset significantly affect their analyses. We propose a framework that can produce automatic contingency analysis, i.e., the range of values an aggregate SQL query could take, under formal constraints describing the variation and frequency of missing data tuples. We describe how to process SUM, COUNT, AVG, MIN, and MAX queries in these conditions resulting in hard error bounds with testable constraints. We propose an optimization algorithm based on an integer program that reconciles a set of suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04139","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/2004.04139/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":"2004.04139","created_at":"2026-07-05T00:53:59.317016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.04139v1","created_at":"2026-07-05T00:53:59.317016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04139","created_at":"2026-07-05T00:53:59.317016+00:00"},{"alias_kind":"pith_short_12","alias_value":"6O7ZBZXODJAU","created_at":"2026-07-05T00:53:59.317016+00:00"},{"alias_kind":"pith_short_16","alias_value":"6O7ZBZXODJAU5TLD","created_at":"2026-07-05T00:53:59.317016+00:00"},{"alias_kind":"pith_short_8","alias_value":"6O7ZBZXO","created_at":"2026-07-05T00:53:59.317016+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/6O7ZBZXODJAU5TLD3D6USCCCZ5","json":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5.json","graph_json":"https://pith.science/api/pith-number/6O7ZBZXODJAU5TLD3D6USCCCZ5/graph.json","events_json":"https://pith.science/api/pith-number/6O7ZBZXODJAU5TLD3D6USCCCZ5/events.json","paper":"https://pith.science/paper/6O7ZBZXO"},"agent_actions":{"view_html":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5","download_json":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5.json","view_paper":"https://pith.science/paper/6O7ZBZXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.04139&json=true","fetch_graph":"https://pith.science/api/pith-number/6O7ZBZXODJAU5TLD3D6USCCCZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/6O7ZBZXODJAU5TLD3D6USCCCZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5/action/storage_attestation","attest_author":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5/action/author_attestation","sign_citation":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5/action/citation_signature","submit_replication":"https://pith.science/pith/6O7ZBZXODJAU5TLD3D6USCCCZ5/action/replication_record"}},"created_at":"2026-07-05T00:53:59.317016+00:00","updated_at":"2026-07-05T00:53:59.317016+00:00"}