{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:TUY4BZFGO5KDPKXBTUITKZUHKW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0765d51bc98e2a30bf83eb2fe2382a9cc6a8ae3d4fee7d1d8b5fabfbd6aa2433","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-17T13:40:31Z","title_canon_sha256":"d0b9ce73de775c90627759d808866a56f18239ba2ac3dcd62bff02be034e1cd0"},"schema_version":"1.0","source":{"id":"1608.04961","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04961","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04961v3","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04961","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"TUY4BZFGO5KD","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"TUY4BZFGO5KDPKXB","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"TUY4BZFG","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:814e3d4cdf4b36fbfa00f0e8f0d2b36b5dc92855ba35c5b7acfa33d53328fe7a","target":"graph","created_at":"2026-05-18T00:31:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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.","authors_text":"Rajiv Sambasivan, Sourish Das","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-17T13:40:31Z","title":"Clustering Mixed Datasets Using Homogeneity Analysis with Applications to Big Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04961","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:46f8a96dd50c17d702d8adcd8eb2b1a57a745e6b6ecb6434ccc0593f8a1d4a74","target":"record","created_at":"2026-05-18T00:31:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0765d51bc98e2a30bf83eb2fe2382a9cc6a8ae3d4fee7d1d8b5fabfbd6aa2433","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-17T13:40:31Z","title_canon_sha256":"d0b9ce73de775c90627759d808866a56f18239ba2ac3dcd62bff02be034e1cd0"},"schema_version":"1.0","source":{"id":"1608.04961","kind":"arxiv","version":3}},"canonical_sha256":"9d31c0e4a6775437aae19d1135668755bbf62242af5fc70af976e83821223666","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d31c0e4a6775437aae19d1135668755bbf62242af5fc70af976e83821223666","first_computed_at":"2026-05-18T00:31:51.954779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:51.954779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SgXBx5bHROUAC9NMzTvLZ4Gu7bfoNxiflRCFCU26nK2qYz45CkXDF1HkORrldqpc0Rd1Oe8oxuM7eT9dRs8FBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:51.955442Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.04961","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46f8a96dd50c17d702d8adcd8eb2b1a57a745e6b6ecb6434ccc0593f8a1d4a74","sha256:814e3d4cdf4b36fbfa00f0e8f0d2b36b5dc92855ba35c5b7acfa33d53328fe7a"],"state_sha256":"002efa78d42767e7bd8a5f81b3c0f4ffadecc97b7bcc2917349fe7b6094573c6"}