{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:TUY4BZFGO5KDPKXBTUITKZUHKW","short_pith_number":"pith:TUY4BZFG","schema_version":"1.0","canonical_sha256":"9d31c0e4a6775437aae19d1135668755bbf62242af5fc70af976e83821223666","source":{"kind":"arxiv","id":"1608.04961","version":3},"attestation_state":"computed","paper":{"title":"Clustering Mixed Datasets Using Homogeneity Analysis with Applications to Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Rajiv Sambasivan, Sourish Das","submitted_at":"2016-08-17T13:40:31Z","abstract_excerpt":"Datasets with a mixture of numerical and categorical attributes are routinely encountered in many application domains. In this work we examine an approach to clustering such datasets using homogeneity analysis. Homogeneity analysis determines a euclidean representation of the data. This can be analyzed by leveraging the large body of tools and techniques for data with a euclidean representation. Experiments conducted as part of this study suggest that this approach can be useful in the analysis and exploration of big datasets with a mixture of numerical and categorical attributes."},"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":"1608.04961","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-17T13:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"d0b9ce73de775c90627759d808866a56f18239ba2ac3dcd62bff02be034e1cd0","abstract_canon_sha256":"0765d51bc98e2a30bf83eb2fe2382a9cc6a8ae3d4fee7d1d8b5fabfbd6aa2433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:51.955442Z","signature_b64":"SgXBx5bHROUAC9NMzTvLZ4Gu7bfoNxiflRCFCU26nK2qYz45CkXDF1HkORrldqpc0Rd1Oe8oxuM7eT9dRs8FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d31c0e4a6775437aae19d1135668755bbf62242af5fc70af976e83821223666","last_reissued_at":"2026-05-18T00:31:51.954779Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:51.954779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering Mixed Datasets Using Homogeneity Analysis with Applications to Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Rajiv Sambasivan, Sourish Das","submitted_at":"2016-08-17T13:40:31Z","abstract_excerpt":"Datasets with a mixture of numerical and categorical attributes are routinely encountered in many application domains. In this work we examine an approach to clustering such datasets using homogeneity analysis. Homogeneity analysis determines a euclidean representation of the data. This can be analyzed by leveraging the large body of tools and techniques for data with a euclidean representation. Experiments conducted as part of this study suggest that this approach can be useful in the analysis and exploration of big datasets with a mixture of numerical and categorical attributes."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04961","kind":"arxiv","version":3},"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":"1608.04961","created_at":"2026-05-18T00:31:51.954882+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.04961v3","created_at":"2026-05-18T00:31:51.954882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04961","created_at":"2026-05-18T00:31:51.954882+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUY4BZFGO5KD","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUY4BZFGO5KDPKXB","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUY4BZFG","created_at":"2026-05-18T12:30:46.583412+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/TUY4BZFGO5KDPKXBTUITKZUHKW","json":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW.json","graph_json":"https://pith.science/api/pith-number/TUY4BZFGO5KDPKXBTUITKZUHKW/graph.json","events_json":"https://pith.science/api/pith-number/TUY4BZFGO5KDPKXBTUITKZUHKW/events.json","paper":"https://pith.science/paper/TUY4BZFG"},"agent_actions":{"view_html":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW","download_json":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW.json","view_paper":"https://pith.science/paper/TUY4BZFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.04961&json=true","fetch_graph":"https://pith.science/api/pith-number/TUY4BZFGO5KDPKXBTUITKZUHKW/graph.json","fetch_events":"https://pith.science/api/pith-number/TUY4BZFGO5KDPKXBTUITKZUHKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW/action/storage_attestation","attest_author":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW/action/author_attestation","sign_citation":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW/action/citation_signature","submit_replication":"https://pith.science/pith/TUY4BZFGO5KDPKXBTUITKZUHKW/action/replication_record"}},"created_at":"2026-05-18T00:31:51.954882+00:00","updated_at":"2026-05-18T00:31:51.954882+00:00"}