{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:M7H655S4O2563EUIU4CHOVGMIJ","short_pith_number":"pith:M7H655S4","schema_version":"1.0","canonical_sha256":"67cfeef65c76bbed9288a7047754cc4274707b64eb23581858e51bf74f9d7428","source":{"kind":"arxiv","id":"1606.05100","version":1},"attestation_state":"computed","paper":{"title":"PECOK: a convex optimization approach to variable clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Christophe Giraud, Florentina Bunea, Martin Royer, Nicolas Verzelen","submitted_at":"2016-06-16T08:58:34Z","abstract_excerpt":"The problem of variable clustering is that of grouping similar components of a $p$-dimensional vector $X=(X_{1},\\ldots,X_{p})$, and estimating these groups from $n$ independent copies of $X$. When cluster similarity is defined via $G$-latent models, in which groups of $X$-variables have a common latent generator, and groups are relative to a partition $G$ of the index set $\\{1, \\ldots, p\\}$, the most natural clustering strategy is $K$-means. We explain why this strategy cannot lead to perfect cluster recovery and offer a correction, based on semi-definite programing, that can be viewed as a pe"},"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":"1606.05100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-06-16T08:58:34Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"3532ba53c1c7a48c5bde9953577d5a27482f7802e45b84783e792f096caa5909","abstract_canon_sha256":"00c2e06a3a4191251552eabd3b0e56f553a0c57c2ee20ef58036eb84350dddd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:22.018973Z","signature_b64":"HWVGS9qzQoBJpVVLC8rXk1T97EY4G8Nf1Wf9x1/6RN5LdEDedAfFsSmOH2Z+3lNgjI7Vyy5atnlPKxHLGp2rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67cfeef65c76bbed9288a7047754cc4274707b64eb23581858e51bf74f9d7428","last_reissued_at":"2026-05-18T01:12:22.018628Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:22.018628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PECOK: a convex optimization approach to variable clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Christophe Giraud, Florentina Bunea, Martin Royer, Nicolas Verzelen","submitted_at":"2016-06-16T08:58:34Z","abstract_excerpt":"The problem of variable clustering is that of grouping similar components of a $p$-dimensional vector $X=(X_{1},\\ldots,X_{p})$, and estimating these groups from $n$ independent copies of $X$. When cluster similarity is defined via $G$-latent models, in which groups of $X$-variables have a common latent generator, and groups are relative to a partition $G$ of the index set $\\{1, \\ldots, p\\}$, the most natural clustering strategy is $K$-means. We explain why this strategy cannot lead to perfect cluster recovery and offer a correction, based on semi-definite programing, that can be viewed as a pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05100","kind":"arxiv","version":1},"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":"1606.05100","created_at":"2026-05-18T01:12:22.018675+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.05100v1","created_at":"2026-05-18T01:12:22.018675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05100","created_at":"2026-05-18T01:12:22.018675+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7H655S4O256","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7H655S4O2563EUI","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7H655S4","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2209.14859","citing_title":"Exact Recovery of Community Detection in dependent Gaussian Mixture Models","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ","json":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ.json","graph_json":"https://pith.science/api/pith-number/M7H655S4O2563EUIU4CHOVGMIJ/graph.json","events_json":"https://pith.science/api/pith-number/M7H655S4O2563EUIU4CHOVGMIJ/events.json","paper":"https://pith.science/paper/M7H655S4"},"agent_actions":{"view_html":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ","download_json":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ.json","view_paper":"https://pith.science/paper/M7H655S4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.05100&json=true","fetch_graph":"https://pith.science/api/pith-number/M7H655S4O2563EUIU4CHOVGMIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/M7H655S4O2563EUIU4CHOVGMIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ/action/storage_attestation","attest_author":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ/action/author_attestation","sign_citation":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ/action/citation_signature","submit_replication":"https://pith.science/pith/M7H655S4O2563EUIU4CHOVGMIJ/action/replication_record"}},"created_at":"2026-05-18T01:12:22.018675+00:00","updated_at":"2026-05-18T01:12:22.018675+00:00"}