{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6WSKZCWAQC2HXH5WXO7IZIXRHN","short_pith_number":"pith:6WSKZCWA","schema_version":"1.0","canonical_sha256":"f5a4ac8ac080b47b9fb6bbbe8ca2f13b63c3fc1d97c8fe3c854bf276dbd46bcb","source":{"kind":"arxiv","id":"1904.02285","version":1},"attestation_state":"computed","paper":{"title":"HoloDetect: Few-Shot Learning for Error Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alireza Heidari, Ihab F. Ilyas, Joshua McGrath, Theodoros Rekatsinas","submitted_at":"2019-04-04T00:38:59Z","abstract_excerpt":"We introduce a few-shot learning framework for error detection. We show that data augmentation (a form of weak supervision) is key to training high-quality, ML-based error detection models that require minimal human involvement. Our framework consists of two parts: (1) an expressive model to learn rich representations that capture the inherent syntactic and semantic heterogeneity of errors; and (2) a data augmentation model that, given a small seed of clean records, uses dataset-specific transformations to automatically generate additional training data. Our key insight is to learn data augmen"},"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":"1904.02285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-04T00:38:59Z","cross_cats_sorted":[],"title_canon_sha256":"88890ab309be359b159874b371123d14f14f0f1572102a24837a21ca6d5a8335","abstract_canon_sha256":"c35f350a2f4d9d5d67400844308df1943f475cccc8a213c81d5016fadf8b4243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:24.036190Z","signature_b64":"xYZAxBeVbxRHr/5tWGHCnvNGC/OivBTmGWOHmKnH+v5VhRwjpXDrHTSO6EIRYokDHlPSnJLkvFi7mJM4VYNcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a4ac8ac080b47b9fb6bbbe8ca2f13b63c3fc1d97c8fe3c854bf276dbd46bcb","last_reissued_at":"2026-05-17T23:49:24.035499Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:24.035499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoloDetect: Few-Shot Learning for Error Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alireza Heidari, Ihab F. Ilyas, Joshua McGrath, Theodoros Rekatsinas","submitted_at":"2019-04-04T00:38:59Z","abstract_excerpt":"We introduce a few-shot learning framework for error detection. We show that data augmentation (a form of weak supervision) is key to training high-quality, ML-based error detection models that require minimal human involvement. Our framework consists of two parts: (1) an expressive model to learn rich representations that capture the inherent syntactic and semantic heterogeneity of errors; and (2) a data augmentation model that, given a small seed of clean records, uses dataset-specific transformations to automatically generate additional training data. Our key insight is to learn data augmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02285","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":"1904.02285","created_at":"2026-05-17T23:49:24.035622+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02285v1","created_at":"2026-05-17T23:49:24.035622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02285","created_at":"2026-05-17T23:49:24.035622+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WSKZCWAQC2H","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WSKZCWAQC2HXH5W","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WSKZCWA","created_at":"2026-05-18T12:33:10.108867+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/6WSKZCWAQC2HXH5WXO7IZIXRHN","json":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN.json","graph_json":"https://pith.science/api/pith-number/6WSKZCWAQC2HXH5WXO7IZIXRHN/graph.json","events_json":"https://pith.science/api/pith-number/6WSKZCWAQC2HXH5WXO7IZIXRHN/events.json","paper":"https://pith.science/paper/6WSKZCWA"},"agent_actions":{"view_html":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN","download_json":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN.json","view_paper":"https://pith.science/paper/6WSKZCWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02285&json=true","fetch_graph":"https://pith.science/api/pith-number/6WSKZCWAQC2HXH5WXO7IZIXRHN/graph.json","fetch_events":"https://pith.science/api/pith-number/6WSKZCWAQC2HXH5WXO7IZIXRHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN/action/storage_attestation","attest_author":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN/action/author_attestation","sign_citation":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN/action/citation_signature","submit_replication":"https://pith.science/pith/6WSKZCWAQC2HXH5WXO7IZIXRHN/action/replication_record"}},"created_at":"2026-05-17T23:49:24.035622+00:00","updated_at":"2026-05-17T23:49:24.035622+00:00"}