{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WTKB7AVWUZPDDRWD6D46KTRPYN","short_pith_number":"pith:WTKB7AVW","schema_version":"1.0","canonical_sha256":"b4d41f82b6a65e31c6c3f0f9e54e2fc35621811dfe2449726946f45076652410","source":{"kind":"arxiv","id":"1905.04616","version":1},"attestation_state":"computed","paper":{"title":"VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.HC","authors_text":"Arvind Satyanarayan, \\c{C}a\\u{g}atay Demiralp, C\\'esar Hidalgo, Emanuel Zgraggen, Guoliang Li, Kevin Hu, Madelon Hulsebos, Michiel Bakker, Neil Gaikwad, Tim Kraska","submitted_at":"2019-05-12T00:47:28Z","abstract_excerpt":"Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the characteristics of real-world datasets, and their one-off nature makes it difficult to compare different techniques. In this paper, we present VizNet: a large-scale corpus of over 31 million datasets compiled from open data repositories and online visualization galleries. On average, these datasets comprise 17 records over 3 dimensions and across the corpus, we find 51% of the dimensions record categorical data, 44% quantit"},"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":"1905.04616","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2019-05-12T00:47:28Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"daa91b6bb3d3a2a033646683a838f793315d3aaaa207a1d1fe3f9a1557bf89ff","abstract_canon_sha256":"593e0c41d38bde93e62e2afbe7bc8a1142a20ef41f8333e084657bd8a5f177b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:24.159259Z","signature_b64":"mL2Et0VbH4A54DvZz1XBr2XlpcnXznUCyaWrIFP6+MojxlpEGPIxby+RIes8larMillFaBi7HDLl4rh2Ax6QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4d41f82b6a65e31c6c3f0f9e54e2fc35621811dfe2449726946f45076652410","last_reissued_at":"2026-05-17T23:46:24.158527Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:24.158527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.HC","authors_text":"Arvind Satyanarayan, \\c{C}a\\u{g}atay Demiralp, C\\'esar Hidalgo, Emanuel Zgraggen, Guoliang Li, Kevin Hu, Madelon Hulsebos, Michiel Bakker, Neil Gaikwad, Tim Kraska","submitted_at":"2019-05-12T00:47:28Z","abstract_excerpt":"Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the characteristics of real-world datasets, and their one-off nature makes it difficult to compare different techniques. In this paper, we present VizNet: a large-scale corpus of over 31 million datasets compiled from open data repositories and online visualization galleries. On average, these datasets comprise 17 records over 3 dimensions and across the corpus, we find 51% of the dimensions record categorical data, 44% quantit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04616","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":"1905.04616","created_at":"2026-05-17T23:46:24.158660+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04616v1","created_at":"2026-05-17T23:46:24.158660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04616","created_at":"2026-05-17T23:46:24.158660+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTKB7AVWUZPD","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTKB7AVWUZPDDRWD","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTKB7AVW","created_at":"2026-05-18T12:33:30.264802+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/WTKB7AVWUZPDDRWD6D46KTRPYN","json":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN.json","graph_json":"https://pith.science/api/pith-number/WTKB7AVWUZPDDRWD6D46KTRPYN/graph.json","events_json":"https://pith.science/api/pith-number/WTKB7AVWUZPDDRWD6D46KTRPYN/events.json","paper":"https://pith.science/paper/WTKB7AVW"},"agent_actions":{"view_html":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN","download_json":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN.json","view_paper":"https://pith.science/paper/WTKB7AVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04616&json=true","fetch_graph":"https://pith.science/api/pith-number/WTKB7AVWUZPDDRWD6D46KTRPYN/graph.json","fetch_events":"https://pith.science/api/pith-number/WTKB7AVWUZPDDRWD6D46KTRPYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN/action/storage_attestation","attest_author":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN/action/author_attestation","sign_citation":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN/action/citation_signature","submit_replication":"https://pith.science/pith/WTKB7AVWUZPDDRWD6D46KTRPYN/action/replication_record"}},"created_at":"2026-05-17T23:46:24.158660+00:00","updated_at":"2026-05-17T23:46:24.158660+00:00"}