{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PO4JOGGP4OERALIKHHES464WPZ","short_pith_number":"pith:PO4JOGGP","canonical_record":{"source":{"id":"2012.02985","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-12-05T09:29:21Z","cross_cats_sorted":["stat.ME","stat.TH"],"title_canon_sha256":"bac451c158501c34eca295c7a8b749eead3efb752ea09920592ff5f134ad7769","abstract_canon_sha256":"6a301b694f74fa533aede1a374d7c93b62e9c2eef320a3ba771f538a92fea34a"},"schema_version":"1.0"},"canonical_sha256":"7bb89718cfe389102d0a39c92e7b967e7ec41f5b5d071c55fb56b2415b404335","source":{"kind":"arxiv","id":"2012.02985","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02985","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02985v5","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02985","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"PO4JOGGP4OER","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"PO4JOGGP4OERALIK","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"PO4JOGGP","created_at":"2026-05-28T02:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PO4JOGGP4OERALIKHHES464WPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02985","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-12-05T09:29:21Z","cross_cats_sorted":["stat.ME","stat.TH"],"title_canon_sha256":"bac451c158501c34eca295c7a8b749eead3efb752ea09920592ff5f134ad7769","abstract_canon_sha256":"6a301b694f74fa533aede1a374d7c93b62e9c2eef320a3ba771f538a92fea34a"},"schema_version":"1.0"},"canonical_sha256":"7bb89718cfe389102d0a39c92e7b967e7ec41f5b5d071c55fb56b2415b404335","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:38.282943Z","signature_b64":"lImTerzShZPzO99rH+S/VgdJDQ3MX4/7hJj8fV6o2CmFtdQ40kukTcuooaLRKFvzla7kdjB4UB24Mg/YtmJkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bb89718cfe389102d0a39c92e7b967e7ec41f5b5d071c55fb56b2415b404335","last_reissued_at":"2026-05-28T02:04:38.282395Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:38.282395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02985","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHHLhP/eT/2viejC7GTrOPF1/Oy2cU1YlkHkqb5ciiRAv2luFjrSBQo98hPaGb95IoUcav0G0kfEvSYmObucBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:21:24.089160Z"},"content_sha256":"41a068d53c47c4ee245b66be970c20b9be713f42c264e34025122da61be1524e","schema_version":"1.0","event_id":"sha256:41a068d53c47c4ee245b66be970c20b9be713f42c264e34025122da61be1524e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PO4JOGGP4OERALIKHHES464WPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selecting the number of components in PCA via random signflips","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"David Hong, Edgar Dobriban, Yue Sheng","submitted_at":"2020-12-05T09:29:21Z","abstract_excerpt":"Principal component analysis (PCA) is a foundational tool in modern data analysis, and a crucial step in PCA is selecting the number of components to keep. However, classical selection methods (e.g., scree plots, parallel analysis, etc.) lack statistical guarantees in the increasingly common setting of large-dimensional data with heterogeneous noise, i.e., where each entry may have a different noise variance. Moreover, it turns out that these methods, which are highly effective for homogeneous noise, can fail dramatically for data with heterogeneous noise. This paper proposes a new method call"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02985","kind":"arxiv","version":5},"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/2012.02985/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GR+HSi2fg5AonA0wBMJT3g/oW2N2MdtoRBkL1QbIF0BM1M85O5+ktNbHmRX7GtVfG/CBQxaju9CocV5e5rPRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:21:24.089558Z"},"content_sha256":"1e2a8832707fd3b6227828fe91c6e26148650396574c6fc429103ec555e2a67a","schema_version":"1.0","event_id":"sha256:1e2a8832707fd3b6227828fe91c6e26148650396574c6fc429103ec555e2a67a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PO4JOGGP4OERALIKHHES464WPZ/bundle.json","state_url":"https://pith.science/pith/PO4JOGGP4OERALIKHHES464WPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PO4JOGGP4OERALIKHHES464WPZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T03:21:24Z","links":{"resolver":"https://pith.science/pith/PO4JOGGP4OERALIKHHES464WPZ","bundle":"https://pith.science/pith/PO4JOGGP4OERALIKHHES464WPZ/bundle.json","state":"https://pith.science/pith/PO4JOGGP4OERALIKHHES464WPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PO4JOGGP4OERALIKHHES464WPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PO4JOGGP4OERALIKHHES464WPZ","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":"6a301b694f74fa533aede1a374d7c93b62e9c2eef320a3ba771f538a92fea34a","cross_cats_sorted":["stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-12-05T09:29:21Z","title_canon_sha256":"bac451c158501c34eca295c7a8b749eead3efb752ea09920592ff5f134ad7769"},"schema_version":"1.0","source":{"id":"2012.02985","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02985","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02985v5","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02985","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"PO4JOGGP4OER","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"PO4JOGGP4OERALIK","created_at":"2026-05-28T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"PO4JOGGP","created_at":"2026-05-28T02:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:1e2a8832707fd3b6227828fe91c6e26148650396574c6fc429103ec555e2a67a","target":"graph","created_at":"2026-05-28T02:04:38Z","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/2012.02985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Principal component analysis (PCA) is a foundational tool in modern data analysis, and a crucial step in PCA is selecting the number of components to keep. However, classical selection methods (e.g., scree plots, parallel analysis, etc.) lack statistical guarantees in the increasingly common setting of large-dimensional data with heterogeneous noise, i.e., where each entry may have a different noise variance. Moreover, it turns out that these methods, which are highly effective for homogeneous noise, can fail dramatically for data with heterogeneous noise. This paper proposes a new method call","authors_text":"David Hong, Edgar Dobriban, Yue Sheng","cross_cats":["stat.ME","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-12-05T09:29:21Z","title":"Selecting the number of components in PCA via random signflips"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02985","kind":"arxiv","version":5},"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":"sha256:41a068d53c47c4ee245b66be970c20b9be713f42c264e34025122da61be1524e","target":"record","created_at":"2026-05-28T02:04:38Z","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":"6a301b694f74fa533aede1a374d7c93b62e9c2eef320a3ba771f538a92fea34a","cross_cats_sorted":["stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-12-05T09:29:21Z","title_canon_sha256":"bac451c158501c34eca295c7a8b749eead3efb752ea09920592ff5f134ad7769"},"schema_version":"1.0","source":{"id":"2012.02985","kind":"arxiv","version":5}},"canonical_sha256":"7bb89718cfe389102d0a39c92e7b967e7ec41f5b5d071c55fb56b2415b404335","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bb89718cfe389102d0a39c92e7b967e7ec41f5b5d071c55fb56b2415b404335","first_computed_at":"2026-05-28T02:04:38.282395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:38.282395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lImTerzShZPzO99rH+S/VgdJDQ3MX4/7hJj8fV6o2CmFtdQ40kukTcuooaLRKFvzla7kdjB4UB24Mg/YtmJkDg==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:38.282943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02985","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a068d53c47c4ee245b66be970c20b9be713f42c264e34025122da61be1524e","sha256:1e2a8832707fd3b6227828fe91c6e26148650396574c6fc429103ec555e2a67a"],"state_sha256":"d8569e8919bd7de362ae4a5a9d7febc14577a9a1fd2c5c1d2b6608d0a699891b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3agTOX+df5XaKA8zT5oXFDPERAIYPBaJZUXNrjxlzGrbF7NwtfhSrNafO59YGfQ7GtrtDkH7Wux6TecXAqQECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T03:21:24.091549Z","bundle_sha256":"44fd37d1464c1db920e91dcf338805e04b91dff0d45e4b837712470db1c03f78"}}