{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2009:D6VH4J5FIXOI3XQMEXIPY5CLGI","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":"aaf2f72f9f94efd9c5c1645b20abc8e9120c67001565f1592e8ff70d7c04a4c5","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2009-09-16T16:16:48Z","title_canon_sha256":"949d0f348911489a92e49779c8ae8259557e4dfc267b5ef018fed0b33f2d5847"},"schema_version":"1.0","source":{"id":"0909.3052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0909.3052","created_at":"2026-07-04T15:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"0909.3052v1","created_at":"2026-07-04T15:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0909.3052","created_at":"2026-07-04T15:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"D6VH4J5FIXOI","created_at":"2026-07-04T15:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"D6VH4J5FIXOI3XQM","created_at":"2026-07-04T15:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"D6VH4J5F","created_at":"2026-07-04T15:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:e31636f93b5a52fc56c0b7e9c2926426ed7db2b992e8afa51a17e40702bf6632","target":"graph","created_at":"2026-07-04T15:49:47Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/0909.3052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-validation (CV) is a popular method for model-selection. Unfortunately, it is not immediately obvious how to apply CV to unsupervised or exploratory contexts. This thesis discusses some extensions of cross-validation to unsupervised learning, specifically focusing on the problem of choosing how many principal components to keep. We introduce the latent factor model, define an objective criterion, and show how CV can be used to estimate the intrinsic dimensionality of a data set. Through both simulation and theory, we demonstrate that cross-validation is a valuable tool for unsupervised l","authors_text":"Patrick O. Perry","cross_cats":["math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2009-09-16T16:16:48Z","title":"Cross-Validation for Unsupervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0909.3052","kind":"arxiv","version":1},"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":"sha256:41259517114ee91ee7afbea18d9195a8cba7b71feec863d8420f7bf2b437dc34","target":"record","created_at":"2026-07-04T15:49:47Z","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":"aaf2f72f9f94efd9c5c1645b20abc8e9120c67001565f1592e8ff70d7c04a4c5","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2009-09-16T16:16:48Z","title_canon_sha256":"949d0f348911489a92e49779c8ae8259557e4dfc267b5ef018fed0b33f2d5847"},"schema_version":"1.0","source":{"id":"0909.3052","kind":"arxiv","version":1}},"canonical_sha256":"1faa7e27a545dc8dde0c25d0fc744b3224932caf13f779adce49ac29ba0f76b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1faa7e27a545dc8dde0c25d0fc744b3224932caf13f779adce49ac29ba0f76b3","first_computed_at":"2026-07-04T15:49:47.143746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T15:49:47.143746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfDAx8GQuN6/aA8nN78A6A4u6sJ9XyPebWbbOHcuK7Wr94dOZeCQDeuvNA2ZLLR9UM+jkaG2y9mRmYLb9kDPCg==","signature_status":"signed_v1","signed_at":"2026-07-04T15:49:47.144142Z","signed_message":"canonical_sha256_bytes"},"source_id":"0909.3052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41259517114ee91ee7afbea18d9195a8cba7b71feec863d8420f7bf2b437dc34","sha256:e31636f93b5a52fc56c0b7e9c2926426ed7db2b992e8afa51a17e40702bf6632"],"state_sha256":"b1b45a6d8adf52737ce21c1e4c7aebd161f466db02797fe023e7eb35952ceed0"}