{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:2ZUIU4AZ4TVCZH57DTBGR42W5X","short_pith_number":"pith:2ZUIU4AZ","schema_version":"1.0","canonical_sha256":"d6688a7019e4ea2c9fbf1cc268f356edecc2b7e779f65602ea6b5eb035f47702","source":{"kind":"arxiv","id":"1611.02648","version":2},"attestation_state":"computed","paper":{"title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugh Salimbeni, Kai Arulkumaran, Marta Garnelo, Matthew C.H. Lee, Murray Shanahan, Nat Dilokthanakul, Pedro A.M. Mediano","submitted_at":"2016-11-08T18:36:36Z","abstract_excerpt":"We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself in our model and leads to cluster degeneracy. We show that a heuristic called minimum information constraint that has been shown to mitigate this effect in VAEs can also be applied to improve unsupervised clustering performance with our model. Furthermore we analyse the effect of "},"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":"1611.02648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-08T18:36:36Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"34dd213c32e251b2181b6bfc792d8a61a26ff4f53c7fa6af10fa03864340d52f","abstract_canon_sha256":"ea4186c20a0153157ab370f882fa3f4698d6729e5edcd5972d4f0d25291b9f24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:54.986233Z","signature_b64":"eBRYVkq8eRGx66AivX3DRmCYa60SZpoAkM+sPofppKbdxg6HcAOj0kR8GkK2FZmEbcG98QZjs0IIvm7UfPJYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6688a7019e4ea2c9fbf1cc268f356edecc2b7e779f65602ea6b5eb035f47702","last_reissued_at":"2026-05-18T00:52:54.985690Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:54.985690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugh Salimbeni, Kai Arulkumaran, Marta Garnelo, Matthew C.H. Lee, Murray Shanahan, Nat Dilokthanakul, Pedro A.M. Mediano","submitted_at":"2016-11-08T18:36:36Z","abstract_excerpt":"We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself in our model and leads to cluster degeneracy. We show that a heuristic called minimum information constraint that has been shown to mitigate this effect in VAEs can also be applied to improve unsupervised clustering performance with our model. Furthermore we analyse the effect of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02648","kind":"arxiv","version":2},"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":"1611.02648","created_at":"2026-05-18T00:52:54.985783+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02648v2","created_at":"2026-05-18T00:52:54.985783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02648","created_at":"2026-05-18T00:52:54.985783+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZUIU4AZ4TVC","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZUIU4AZ4TVCZH57","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZUIU4AZ","created_at":"2026-05-18T12:29:55.572404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.15640","citing_title":"Learning Disentangled Representations for Generalized Multi-view Clustering","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2507.05454","citing_title":"Risk-Aware Aerocapture Guidance Through a Probabilistic Indicator Function","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2509.02154","citing_title":"Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23547","citing_title":"PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05813","citing_title":"A Testable Certificate for Constant Collapse in Teacher-Guided VAEs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07938","citing_title":"Prototype Guided Post-pretraining for Single-Cell Representation Learning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05513","citing_title":"From Unsupervised to Guided Clustering: A Variational Implementation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X","json":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X.json","graph_json":"https://pith.science/api/pith-number/2ZUIU4AZ4TVCZH57DTBGR42W5X/graph.json","events_json":"https://pith.science/api/pith-number/2ZUIU4AZ4TVCZH57DTBGR42W5X/events.json","paper":"https://pith.science/paper/2ZUIU4AZ"},"agent_actions":{"view_html":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X","download_json":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X.json","view_paper":"https://pith.science/paper/2ZUIU4AZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02648&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZUIU4AZ4TVCZH57DTBGR42W5X/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZUIU4AZ4TVCZH57DTBGR42W5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X/action/storage_attestation","attest_author":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X/action/author_attestation","sign_citation":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X/action/citation_signature","submit_replication":"https://pith.science/pith/2ZUIU4AZ4TVCZH57DTBGR42W5X/action/replication_record"}},"created_at":"2026-05-18T00:52:54.985783+00:00","updated_at":"2026-05-18T00:52:54.985783+00:00"}