{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CCK3BX4ZERPRQJ43ZJ426DBPQP","short_pith_number":"pith:CCK3BX4Z","schema_version":"1.0","canonical_sha256":"1095b0df99245f18279bca79af0c2f83de6c9109ae0ac9cf899a8a9703a14d57","source":{"kind":"arxiv","id":"1910.08018","version":2},"attestation_state":"computed","paper":{"title":"A Unified Framework for Tuning Hyperparameters in Clustering Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Purnamrita Sarkar, Xinjie Fan, Yuguang Yue, Y. X. Rachel Wang","submitted_at":"2019-10-17T16:40:42Z","abstract_excerpt":"Selecting hyperparameters for unsupervised learning problems is challenging in general due to the lack of ground truth for validation. Despite the prevalence of this issue in statistics and machine learning, especially in clustering problems, there are not many methods for tuning these hyperparameters with theoretical guarantees. In this paper, we provide a framework with provable guarantees for selecting hyperparameters in a number of distinct models. We consider both the subgaussian mixture model and network models to serve as examples of i.i.d. and non-i.i.d. data. We demonstrate that the s"},"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":"1910.08018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-17T16:40:42Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"194ae0c4cc65bae97e7820eed9824b96da8dc3f8a835596140609256b0300243","abstract_canon_sha256":"cc902473a79857327d3ce08ba2198c4f06786b689f30f36275336963da16d5a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:48.568789Z","signature_b64":"2qf7KCBYMvFQ6OtmfT5W0O8cBbVrQWWowLsaqkReJQHlLjnucd4aLZmv4ZL1iPexkG02w5ZAubRP6DbFYJ9/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1095b0df99245f18279bca79af0c2f83de6c9109ae0ac9cf899a8a9703a14d57","last_reissued_at":"2026-07-05T00:37:48.568334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:48.568334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Framework for Tuning Hyperparameters in Clustering Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Purnamrita Sarkar, Xinjie Fan, Yuguang Yue, Y. X. Rachel Wang","submitted_at":"2019-10-17T16:40:42Z","abstract_excerpt":"Selecting hyperparameters for unsupervised learning problems is challenging in general due to the lack of ground truth for validation. Despite the prevalence of this issue in statistics and machine learning, especially in clustering problems, there are not many methods for tuning these hyperparameters with theoretical guarantees. In this paper, we provide a framework with provable guarantees for selecting hyperparameters in a number of distinct models. We consider both the subgaussian mixture model and network models to serve as examples of i.i.d. and non-i.i.d. data. We demonstrate that the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08018","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/1910.08018/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":"1910.08018","created_at":"2026-07-05T00:37:48.568400+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.08018v2","created_at":"2026-07-05T00:37:48.568400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08018","created_at":"2026-07-05T00:37:48.568400+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCK3BX4ZERPR","created_at":"2026-07-05T00:37:48.568400+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCK3BX4ZERPRQJ43","created_at":"2026-07-05T00:37:48.568400+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCK3BX4Z","created_at":"2026-07-05T00:37:48.568400+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/CCK3BX4ZERPRQJ43ZJ426DBPQP","json":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP.json","graph_json":"https://pith.science/api/pith-number/CCK3BX4ZERPRQJ43ZJ426DBPQP/graph.json","events_json":"https://pith.science/api/pith-number/CCK3BX4ZERPRQJ43ZJ426DBPQP/events.json","paper":"https://pith.science/paper/CCK3BX4Z"},"agent_actions":{"view_html":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP","download_json":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP.json","view_paper":"https://pith.science/paper/CCK3BX4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.08018&json=true","fetch_graph":"https://pith.science/api/pith-number/CCK3BX4ZERPRQJ43ZJ426DBPQP/graph.json","fetch_events":"https://pith.science/api/pith-number/CCK3BX4ZERPRQJ43ZJ426DBPQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP/action/storage_attestation","attest_author":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP/action/author_attestation","sign_citation":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP/action/citation_signature","submit_replication":"https://pith.science/pith/CCK3BX4ZERPRQJ43ZJ426DBPQP/action/replication_record"}},"created_at":"2026-07-05T00:37:48.568400+00:00","updated_at":"2026-07-05T00:37:48.568400+00:00"}