{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4FRO7NZANAYMSMRD24OHNN27TM","short_pith_number":"pith:4FRO7NZA","schema_version":"1.0","canonical_sha256":"e162efb7206830c93223d71c76b75f9b11eaede592265334d177b0793a3ac02d","source":{"kind":"arxiv","id":"1811.00102","version":2},"attestation_state":"computed","paper":{"title":"On the Persistence of Clustering Solutions and True Number of Clusters in a Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amber Srivastava, Mayank Baranwal, Srinivasa Salapaka","submitted_at":"2018-10-31T20:27:16Z","abstract_excerpt":"Typically clustering algorithms provide clustering solutions with prespecified number of clusters. The lack of a priori knowledge on the true number of underlying clusters in the dataset makes it important to have a metric to compare the clustering solutions with different number of clusters. This article quantifies a notion of persistence of clustering solutions that enables comparing solutions with different number of clusters. The persistence relates to the range of data-resolution scales over which a clustering solution persists; it is quantified in terms of the maximum over two-norms of a"},"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":"1811.00102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T20:27:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"72286c283edef32d15320561ec644a81185f175cdafe633eda46ab00a1b353ac","abstract_canon_sha256":"f18dc492c9783f2cffa724a9d76c90477bedca4e7f9cc06dbfc92327b88c17d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.479156Z","signature_b64":"HcoHhNVCflz+38CmCdEGoeSwlLT8HqhPMU3lV2z3mVkEfTVQM//y3CCbMqLB1lEj9UEfUp1rb4/xLnCIir9kAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e162efb7206830c93223d71c76b75f9b11eaede592265334d177b0793a3ac02d","last_reissued_at":"2026-05-18T00:00:29.478640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.478640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Persistence of Clustering Solutions and True Number of Clusters in a Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amber Srivastava, Mayank Baranwal, Srinivasa Salapaka","submitted_at":"2018-10-31T20:27:16Z","abstract_excerpt":"Typically clustering algorithms provide clustering solutions with prespecified number of clusters. The lack of a priori knowledge on the true number of underlying clusters in the dataset makes it important to have a metric to compare the clustering solutions with different number of clusters. This article quantifies a notion of persistence of clustering solutions that enables comparing solutions with different number of clusters. The persistence relates to the range of data-resolution scales over which a clustering solution persists; it is quantified in terms of the maximum over two-norms of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00102","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":""},"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":"1811.00102","created_at":"2026-05-18T00:00:29.478717+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00102v2","created_at":"2026-05-18T00:00:29.478717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00102","created_at":"2026-05-18T00:00:29.478717+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FRO7NZANAYM","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FRO7NZANAYMSMRD","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FRO7NZA","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05783","citing_title":"Improving the Projection of Global Structures in Data through Spanning Trees","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM","json":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM.json","graph_json":"https://pith.science/api/pith-number/4FRO7NZANAYMSMRD24OHNN27TM/graph.json","events_json":"https://pith.science/api/pith-number/4FRO7NZANAYMSMRD24OHNN27TM/events.json","paper":"https://pith.science/paper/4FRO7NZA"},"agent_actions":{"view_html":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM","download_json":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM.json","view_paper":"https://pith.science/paper/4FRO7NZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00102&json=true","fetch_graph":"https://pith.science/api/pith-number/4FRO7NZANAYMSMRD24OHNN27TM/graph.json","fetch_events":"https://pith.science/api/pith-number/4FRO7NZANAYMSMRD24OHNN27TM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM/action/storage_attestation","attest_author":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM/action/author_attestation","sign_citation":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM/action/citation_signature","submit_replication":"https://pith.science/pith/4FRO7NZANAYMSMRD24OHNN27TM/action/replication_record"}},"created_at":"2026-05-18T00:00:29.478717+00:00","updated_at":"2026-05-18T00:00:29.478717+00:00"}