{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6CTI6LC27AG7KFV3VPVHAMTGOH","short_pith_number":"pith:6CTI6LC2","schema_version":"1.0","canonical_sha256":"f0a68f2c5af80df516bbabea70326671fbd33788ae19ba03d171ce86330c3efe","source":{"kind":"arxiv","id":"2211.05183","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew C. Gallagher, Michael C. Mozer, Ting Liu, Tyler R. Scott","submitted_at":"2022-11-09T20:26:40Z","abstract_excerpt":"Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods -- including $k$-means and hierarchical agglomerative clustering -- underperform supervised, deep, inductive methods. While the reported improvements are indeed impressive, experiments are mostly limited to face datasets, where the clustered embeddings are highly discriminative or well-separated by class (Recall@1 above 90% and often nearing ceiling), and the experimental methodology seemingly favors the deep methods. We conduct a large-scale empirical study of 17 clustering methods acro"},"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":"2211.05183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-09T20:26:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84fb6a9e61c7c9687864c13a6cfc92581371fbc678fdd359e67301715a8d16cc","abstract_canon_sha256":"13dfaa50096c64802e5bc8debe173bbf497f6ced468090d9c64a00e29f11badb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:47.452730Z","signature_b64":"nAIllTFaFLJPuGqVo71Z5nUzyDUfusraFik/ONjEKeGu0xSt0jUPB++ob7INt0qMBlCpblnUjcEv46glEJMvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0a68f2c5af80df516bbabea70326671fbd33788ae19ba03d171ce86330c3efe","last_reissued_at":"2026-07-05T05:14:47.452183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:47.452183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew C. Gallagher, Michael C. Mozer, Ting Liu, Tyler R. Scott","submitted_at":"2022-11-09T20:26:40Z","abstract_excerpt":"Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods -- including $k$-means and hierarchical agglomerative clustering -- underperform supervised, deep, inductive methods. While the reported improvements are indeed impressive, experiments are mostly limited to face datasets, where the clustered embeddings are highly discriminative or well-separated by class (Recall@1 above 90% and often nearing ceiling), and the experimental methodology seemingly favors the deep methods. We conduct a large-scale empirical study of 17 clustering methods acro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05183","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.05183/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.05183","created_at":"2026-07-05T05:14:47.452240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05183v1","created_at":"2026-07-05T05:14:47.452240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05183","created_at":"2026-07-05T05:14:47.452240+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CTI6LC27AG7","created_at":"2026-07-05T05:14:47.452240+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CTI6LC27AG7KFV3","created_at":"2026-07-05T05:14:47.452240+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CTI6LC2","created_at":"2026-07-05T05:14:47.452240+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21278","citing_title":"Hyperspherical Variational Autoencoders Using Efficient Spherical Cauchy Distribution","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH","json":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH.json","graph_json":"https://pith.science/api/pith-number/6CTI6LC27AG7KFV3VPVHAMTGOH/graph.json","events_json":"https://pith.science/api/pith-number/6CTI6LC27AG7KFV3VPVHAMTGOH/events.json","paper":"https://pith.science/paper/6CTI6LC2"},"agent_actions":{"view_html":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH","download_json":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH.json","view_paper":"https://pith.science/paper/6CTI6LC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05183&json=true","fetch_graph":"https://pith.science/api/pith-number/6CTI6LC27AG7KFV3VPVHAMTGOH/graph.json","fetch_events":"https://pith.science/api/pith-number/6CTI6LC27AG7KFV3VPVHAMTGOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH/action/storage_attestation","attest_author":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH/action/author_attestation","sign_citation":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH/action/citation_signature","submit_replication":"https://pith.science/pith/6CTI6LC27AG7KFV3VPVHAMTGOH/action/replication_record"}},"created_at":"2026-07-05T05:14:47.452240+00:00","updated_at":"2026-07-05T05:14:47.452240+00:00"}