{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U2T3PT5SF6XU7PSMXTSNCPNTV7","short_pith_number":"pith:U2T3PT5S","schema_version":"1.0","canonical_sha256":"a6a7b7cfb22faf4fbe4cbce4d13db3afdb9e4318d9965a8f3e3df6491bb4a2c3","source":{"kind":"arxiv","id":"2310.02656","version":2},"attestation_state":"computed","paper":{"title":"Blend: A Unified Data Discovery System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christoph Schnell, Mahdi Esmailoghli, Ren\\'ee J. Miller, Ziawasch Abedjan","submitted_at":"2023-10-04T08:27:43Z","abstract_excerpt":"Most research on data discovery has so far focused on improving individual discovery operators such as join, correlation, or union discovery. However, in practice, a combination of these techniques and their corresponding indexes may be necessary to support arbitrary discovery tasks. We propose BLEND, a comprehensive data discovery system that supports existing operators and enables their flexible pipelining. BLEND is based on a set of lower-level operators that serve as fundamental building blocks for more complex and sophisticated user tasks. To reduce the execution runtime of discovery pipe"},"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":"2310.02656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-10-04T08:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"5f009f0f614be366286ff56f3f84076428bc958aa6882e60051cf97a1e9cccc2","abstract_canon_sha256":"18fa4b868c6065146461e84042cb2e568ec416535f1518c4a5f6295b7c367159"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:28.822607Z","signature_b64":"bv8jyQuQqpOmsijzLf9OlWxoGqo6QlVkoS7emusKCm213uCl202vhLTMhp4bbuvHwNbihZ3bXS5/DZxelMPwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6a7b7cfb22faf4fbe4cbce4d13db3afdb9e4318d9965a8f3e3df6491bb4a2c3","last_reissued_at":"2026-07-05T09:41:28.822120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:28.822120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blend: A Unified Data Discovery System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christoph Schnell, Mahdi Esmailoghli, Ren\\'ee J. Miller, Ziawasch Abedjan","submitted_at":"2023-10-04T08:27:43Z","abstract_excerpt":"Most research on data discovery has so far focused on improving individual discovery operators such as join, correlation, or union discovery. However, in practice, a combination of these techniques and their corresponding indexes may be necessary to support arbitrary discovery tasks. We propose BLEND, a comprehensive data discovery system that supports existing operators and enables their flexible pipelining. BLEND is based on a set of lower-level operators that serve as fundamental building blocks for more complex and sophisticated user tasks. To reduce the execution runtime of discovery pipe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02656","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/2310.02656/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":"2310.02656","created_at":"2026-07-05T09:41:28.822179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02656v2","created_at":"2026-07-05T09:41:28.822179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02656","created_at":"2026-07-05T09:41:28.822179+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2T3PT5SF6XU","created_at":"2026-07-05T09:41:28.822179+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2T3PT5SF6XU7PSM","created_at":"2026-07-05T09:41:28.822179+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2T3PT5S","created_at":"2026-07-05T09:41:28.822179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22766","citing_title":"Diversed Model Discovery via Structured Table Discovery","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7","json":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7.json","graph_json":"https://pith.science/api/pith-number/U2T3PT5SF6XU7PSMXTSNCPNTV7/graph.json","events_json":"https://pith.science/api/pith-number/U2T3PT5SF6XU7PSMXTSNCPNTV7/events.json","paper":"https://pith.science/paper/U2T3PT5S"},"agent_actions":{"view_html":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7","download_json":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7.json","view_paper":"https://pith.science/paper/U2T3PT5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02656&json=true","fetch_graph":"https://pith.science/api/pith-number/U2T3PT5SF6XU7PSMXTSNCPNTV7/graph.json","fetch_events":"https://pith.science/api/pith-number/U2T3PT5SF6XU7PSMXTSNCPNTV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7/action/storage_attestation","attest_author":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7/action/author_attestation","sign_citation":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7/action/citation_signature","submit_replication":"https://pith.science/pith/U2T3PT5SF6XU7PSMXTSNCPNTV7/action/replication_record"}},"created_at":"2026-07-05T09:41:28.822179+00:00","updated_at":"2026-07-05T09:41:28.822179+00:00"}