{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S4IJD2TYPKKSH7AV53327DDS3Z","short_pith_number":"pith:S4IJD2TY","schema_version":"1.0","canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","source":{"kind":"arxiv","id":"2607.25356","version":1},"attestation_state":"computed","paper":{"title":"Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Laure Berti-Equille","submitted_at":"2026-07-28T07:03:50Z","abstract_excerpt":"Data quality profiling -- computing missing-value rates, duplicate fractions, outlier densities, and functional-dependency violations -- is foundational for data-centric AI pipelines, yet exhaustive scans over millions of rows are prohibitively slow for near-real-time monitoring. Progressive sampling is the standard alternative; the open question is which strategy best preserves profile fidelity at scale. We benchmark nine sampling strategies -- blind (random uniform, geometric, Yamane, cluster) and proxy-guided (Metropolis-Hastings, DAG, stratified by column type or quality score, importance-"},"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":"2607.25356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-28T07:03:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bdfa3d43780894aab22e89d1e8fbdb546d8cafd29a79698dde88dab9830322af","abstract_canon_sha256":"48b3de31e170afa00046ef86d5bd179a941eb778543b0b8df8a2a103d77bace4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:11.082829Z","signature_b64":"RHnIniTUEwBoImK1ZRIUzEcSPnpBxfL2H35mekCmkjVkId+VmlPQ6Wo3ywLK+CjeQ3wuPutd73KQMEI+ZypjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","last_reissued_at":"2026-07-29T01:25:11.082001Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:11.082001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Laure Berti-Equille","submitted_at":"2026-07-28T07:03:50Z","abstract_excerpt":"Data quality profiling -- computing missing-value rates, duplicate fractions, outlier densities, and functional-dependency violations -- is foundational for data-centric AI pipelines, yet exhaustive scans over millions of rows are prohibitively slow for near-real-time monitoring. Progressive sampling is the standard alternative; the open question is which strategy best preserves profile fidelity at scale. We benchmark nine sampling strategies -- blind (random uniform, geometric, Yamane, cluster) and proxy-guided (Metropolis-Hastings, DAG, stratified by column type or quality score, importance-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25356","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/2607.25356/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":"2607.25356","created_at":"2026-07-29T01:25:11.082436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25356v1","created_at":"2026-07-29T01:25:11.082436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25356","created_at":"2026-07-29T01:25:11.082436+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4IJD2TYPKKS","created_at":"2026-07-29T01:25:11.082436+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4IJD2TYPKKSH7AV","created_at":"2026-07-29T01:25:11.082436+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4IJD2TY","created_at":"2026-07-29T01:25:11.082436+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/S4IJD2TYPKKSH7AV53327DDS3Z","json":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z.json","graph_json":"https://pith.science/api/pith-number/S4IJD2TYPKKSH7AV53327DDS3Z/graph.json","events_json":"https://pith.science/api/pith-number/S4IJD2TYPKKSH7AV53327DDS3Z/events.json","paper":"https://pith.science/paper/S4IJD2TY"},"agent_actions":{"view_html":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z","download_json":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z.json","view_paper":"https://pith.science/paper/S4IJD2TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25356&json=true","fetch_graph":"https://pith.science/api/pith-number/S4IJD2TYPKKSH7AV53327DDS3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/S4IJD2TYPKKSH7AV53327DDS3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/action/storage_attestation","attest_author":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/action/author_attestation","sign_citation":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/action/citation_signature","submit_replication":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/action/replication_record"}},"created_at":"2026-07-29T01:25:11.082436+00:00","updated_at":"2026-07-29T01:25:11.082436+00:00"}