{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:55AFRLEMPW7VQ5DON72D7G42JZ","short_pith_number":"pith:55AFRLEM","schema_version":"1.0","canonical_sha256":"ef4058ac8c7dbf58746e6ff43f9b9a4e52e0c15af5823b5ea145284168ccf6c1","source":{"kind":"arxiv","id":"2504.02150","version":1},"attestation_state":"computed","paper":{"title":"LakeVisage: Towards Scalable, Flexible and Interactive Visualization Recommendation for Data Discovery over Data Lakes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jin Wang, Sajjadur Rahman, Yihao Hu","submitted_at":"2025-04-02T21:49:43Z","abstract_excerpt":"Data discovery from data lakes is an essential application in modern data science. While many previous studies focused on improving the efficiency and effectiveness of data discovery, little attention has been paid to the usability of such applications. In particular, exploring data discovery results can be cumbersome due to the cognitive load involved in understanding raw tabular results and identifying insights to draw conclusions. To address this challenge, we introduce a new problem -- visualization recommendation for data discovery over data lakes -- which aims at automatically identifyin"},"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":"2504.02150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-02T21:49:43Z","cross_cats_sorted":[],"title_canon_sha256":"a879caaedbade9bc2565d5b212f523cfcc3c835c6c1e4f6a9ff18d0b2ede9db0","abstract_canon_sha256":"09c89faa032aafd8f13f5d815d99cc6843c60eef0f41897c345c83e072477b9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:51.395593Z","signature_b64":"H+6sfteg+Z7pZ/os9m7KcJlUMHPceXTmumUr2H931oNVf0A7Y2wzsuTLBLI9SmLkmr20VQO0AGiZ4PPVmN1CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef4058ac8c7dbf58746e6ff43f9b9a4e52e0c15af5823b5ea145284168ccf6c1","last_reissued_at":"2026-07-05T10:43:51.395094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:51.395094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LakeVisage: Towards Scalable, Flexible and Interactive Visualization Recommendation for Data Discovery over Data Lakes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jin Wang, Sajjadur Rahman, Yihao Hu","submitted_at":"2025-04-02T21:49:43Z","abstract_excerpt":"Data discovery from data lakes is an essential application in modern data science. While many previous studies focused on improving the efficiency and effectiveness of data discovery, little attention has been paid to the usability of such applications. In particular, exploring data discovery results can be cumbersome due to the cognitive load involved in understanding raw tabular results and identifying insights to draw conclusions. To address this challenge, we introduce a new problem -- visualization recommendation for data discovery over data lakes -- which aims at automatically identifyin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02150","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/2504.02150/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":"2504.02150","created_at":"2026-07-05T10:43:51.395153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02150v1","created_at":"2026-07-05T10:43:51.395153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02150","created_at":"2026-07-05T10:43:51.395153+00:00"},{"alias_kind":"pith_short_12","alias_value":"55AFRLEMPW7V","created_at":"2026-07-05T10:43:51.395153+00:00"},{"alias_kind":"pith_short_16","alias_value":"55AFRLEMPW7VQ5DO","created_at":"2026-07-05T10:43:51.395153+00:00"},{"alias_kind":"pith_short_8","alias_value":"55AFRLEM","created_at":"2026-07-05T10:43:51.395153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22758","citing_title":"RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ","json":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ.json","graph_json":"https://pith.science/api/pith-number/55AFRLEMPW7VQ5DON72D7G42JZ/graph.json","events_json":"https://pith.science/api/pith-number/55AFRLEMPW7VQ5DON72D7G42JZ/events.json","paper":"https://pith.science/paper/55AFRLEM"},"agent_actions":{"view_html":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ","download_json":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ.json","view_paper":"https://pith.science/paper/55AFRLEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02150&json=true","fetch_graph":"https://pith.science/api/pith-number/55AFRLEMPW7VQ5DON72D7G42JZ/graph.json","fetch_events":"https://pith.science/api/pith-number/55AFRLEMPW7VQ5DON72D7G42JZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ/action/storage_attestation","attest_author":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ/action/author_attestation","sign_citation":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ/action/citation_signature","submit_replication":"https://pith.science/pith/55AFRLEMPW7VQ5DON72D7G42JZ/action/replication_record"}},"created_at":"2026-07-05T10:43:51.395153+00:00","updated_at":"2026-07-05T10:43:51.395153+00:00"}