{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HQRN77O62LZIUNGVZWFWBXAIL5","short_pith_number":"pith:HQRN77O6","schema_version":"1.0","canonical_sha256":"3c22dffdded2f28a34d5cd8b60dc085f45df97a9ca21f388995b521640af8fb5","source":{"kind":"arxiv","id":"2410.16124","version":1},"attestation_state":"computed","paper":{"title":"MNIST-Nd: a set of naturalistic datasets to benchmark clustering across dimensions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander S. Ecker, Laura Hansel, Marissa A. Weis, Martin Ritzert, Polina Turishcheva","submitted_at":"2024-10-21T15:51:30Z","abstract_excerpt":"Driven by advances in recording technology, large-scale high-dimensional datasets have emerged across many scientific disciplines. Especially in biology, clustering is often used to gain insights into the structure of such datasets, for instance to understand the organization of different cell types. However, clustering is known to scale poorly to high dimensions, even though the exact impact of dimensionality is unclear as current benchmark datasets are mostly two-dimensional. Here we propose MNIST-Nd, a set of synthetic datasets that share a key property of real-world datasets, namely that i"},"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":"2410.16124","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T15:51:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"19da1b0ce4fda6510e1d2cb7623cf2702681f0a54c370c5a8e0069fb9548e55f","abstract_canon_sha256":"dec07cf327a5046d21680e1e18edc957839c9c4771f0072eebf779c4b70b6657"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:30.173370Z","signature_b64":"fRLsgqkDjSFGwqaC6nV91QGmchLYrHQwMiz9292kRCYeG+BWSE/oJ8LE4+hSz49Z1nYv1YZ/ej8ufsjhVBZUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c22dffdded2f28a34d5cd8b60dc085f45df97a9ca21f388995b521640af8fb5","last_reissued_at":"2026-07-05T09:23:30.172859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:30.172859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MNIST-Nd: a set of naturalistic datasets to benchmark clustering across dimensions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander S. Ecker, Laura Hansel, Marissa A. Weis, Martin Ritzert, Polina Turishcheva","submitted_at":"2024-10-21T15:51:30Z","abstract_excerpt":"Driven by advances in recording technology, large-scale high-dimensional datasets have emerged across many scientific disciplines. Especially in biology, clustering is often used to gain insights into the structure of such datasets, for instance to understand the organization of different cell types. However, clustering is known to scale poorly to high dimensions, even though the exact impact of dimensionality is unclear as current benchmark datasets are mostly two-dimensional. Here we propose MNIST-Nd, a set of synthetic datasets that share a key property of real-world datasets, namely that i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16124","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/2410.16124/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":"2410.16124","created_at":"2026-07-05T09:23:30.172925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16124v1","created_at":"2026-07-05T09:23:30.172925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16124","created_at":"2026-07-05T09:23:30.172925+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQRN77O62LZI","created_at":"2026-07-05T09:23:30.172925+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQRN77O62LZIUNGV","created_at":"2026-07-05T09:23:30.172925+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQRN77O6","created_at":"2026-07-05T09:23:30.172925+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/HQRN77O62LZIUNGVZWFWBXAIL5","json":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5.json","graph_json":"https://pith.science/api/pith-number/HQRN77O62LZIUNGVZWFWBXAIL5/graph.json","events_json":"https://pith.science/api/pith-number/HQRN77O62LZIUNGVZWFWBXAIL5/events.json","paper":"https://pith.science/paper/HQRN77O6"},"agent_actions":{"view_html":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5","download_json":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5.json","view_paper":"https://pith.science/paper/HQRN77O6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16124&json=true","fetch_graph":"https://pith.science/api/pith-number/HQRN77O62LZIUNGVZWFWBXAIL5/graph.json","fetch_events":"https://pith.science/api/pith-number/HQRN77O62LZIUNGVZWFWBXAIL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5/action/storage_attestation","attest_author":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5/action/author_attestation","sign_citation":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5/action/citation_signature","submit_replication":"https://pith.science/pith/HQRN77O62LZIUNGVZWFWBXAIL5/action/replication_record"}},"created_at":"2026-07-05T09:23:30.172925+00:00","updated_at":"2026-07-05T09:23:30.172925+00:00"}