{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BAKCVIVTEY4KMO2TNBZITMGLIY","short_pith_number":"pith:BAKCVIVT","schema_version":"1.0","canonical_sha256":"08142aa2b32638a63b53687289b0cb46076093e058986441766d096b84b5b430","source":{"kind":"arxiv","id":"2506.06147","version":1},"attestation_state":"computed","paper":{"title":"Stream DaQ: Stream-First Data Quality Monitoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anastasios Gounaris, Vasileios Papastergios","submitted_at":"2025-06-06T15:09:32Z","abstract_excerpt":"Data quality is fundamental to modern data science workflows, where data continuously flows as unbounded streams feeding critical downstream tasks, from elementary analytics to advanced artificial intelligence models. Existing data quality approaches either focus exclusively on static data or treat streaming as an extension of batch processing, lacking the temporal granularity and contextual awareness required for true streaming applications. In this paper, we present a novel data quality monitoring model specifically designed for unbounded data streams. Our model introduces stream-first conce"},"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":"2506.06147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-06T15:09:32Z","cross_cats_sorted":[],"title_canon_sha256":"d769585cb0ff256bad8ba9133a10b5d6562e1f87e982015e496f224bfc772b1f","abstract_canon_sha256":"55fddb79ac4edef716f26514ded3151a0142b6cd4556bac1a2e5f0623a5f7232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:26.541439Z","signature_b64":"pTY9ikZvi4QrOW3WaN1J/VbTxmmjLJsYuZIIvqKaNtR4i9lf2owdesTO9UG7+voyChpryYyzImhomKujp46KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08142aa2b32638a63b53687289b0cb46076093e058986441766d096b84b5b430","last_reissued_at":"2026-07-05T11:17:26.540684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:26.540684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stream DaQ: Stream-First Data Quality Monitoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anastasios Gounaris, Vasileios Papastergios","submitted_at":"2025-06-06T15:09:32Z","abstract_excerpt":"Data quality is fundamental to modern data science workflows, where data continuously flows as unbounded streams feeding critical downstream tasks, from elementary analytics to advanced artificial intelligence models. Existing data quality approaches either focus exclusively on static data or treat streaming as an extension of batch processing, lacking the temporal granularity and contextual awareness required for true streaming applications. In this paper, we present a novel data quality monitoring model specifically designed for unbounded data streams. Our model introduces stream-first conce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06147","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/2506.06147/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":"2506.06147","created_at":"2026-07-05T11:17:26.540781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06147v1","created_at":"2026-07-05T11:17:26.540781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06147","created_at":"2026-07-05T11:17:26.540781+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAKCVIVTEY4K","created_at":"2026-07-05T11:17:26.540781+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAKCVIVTEY4KMO2T","created_at":"2026-07-05T11:17:26.540781+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAKCVIVT","created_at":"2026-07-05T11:17:26.540781+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/BAKCVIVTEY4KMO2TNBZITMGLIY","json":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY.json","graph_json":"https://pith.science/api/pith-number/BAKCVIVTEY4KMO2TNBZITMGLIY/graph.json","events_json":"https://pith.science/api/pith-number/BAKCVIVTEY4KMO2TNBZITMGLIY/events.json","paper":"https://pith.science/paper/BAKCVIVT"},"agent_actions":{"view_html":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY","download_json":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY.json","view_paper":"https://pith.science/paper/BAKCVIVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06147&json=true","fetch_graph":"https://pith.science/api/pith-number/BAKCVIVTEY4KMO2TNBZITMGLIY/graph.json","fetch_events":"https://pith.science/api/pith-number/BAKCVIVTEY4KMO2TNBZITMGLIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY/action/storage_attestation","attest_author":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY/action/author_attestation","sign_citation":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY/action/citation_signature","submit_replication":"https://pith.science/pith/BAKCVIVTEY4KMO2TNBZITMGLIY/action/replication_record"}},"created_at":"2026-07-05T11:17:26.540781+00:00","updated_at":"2026-07-05T11:17:26.540781+00:00"}