{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4R7XNVJWDNS7AFMZNUCWXXFKEU","short_pith_number":"pith:4R7XNVJW","schema_version":"1.0","canonical_sha256":"e47f76d5361b65f015996d056bdcaa25001affe576dc2c07b5b0d4fc5101d0c6","source":{"kind":"arxiv","id":"2201.10000","version":1},"attestation_state":"computed","paper":{"title":"Neural Manifold Clustering and Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Friedrich T. Sommer, Yann LeCun, Yubei Chen, Zengyi Li","submitted_at":"2022-01-24T23:13:37Z","abstract_excerpt":"Given a union of non-linear manifolds, non-linear subspace clustering or manifold clustering aims to cluster data points based on manifold structures and also learn to parameterize each manifold as a linear subspace in a feature space. Deep neural networks have the potential to achieve this goal under highly non-linear settings given their large capacity and flexibility. We argue that achieving manifold clustering with neural networks requires two essential ingredients: a domain-specific constraint that ensures the identification of the manifolds, and a learning algorithm for embedding each ma"},"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":"2201.10000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-24T23:13:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1d3efcd16ffbe50867979276c135dd7f33b5ee6d33647ac6c332cb63f5f1f5a3","abstract_canon_sha256":"836fe5ec8216127cf888e0f6d5f520dd8c32d7cd1f795a14827d0453933fdbfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:14.579892Z","signature_b64":"eHG+E0hEIvd/4P8afCrT9+QgdiBj3OrGrRXSOLp55F9ngJc+Hbe1ELtrGIx7JOEa37fJCsrG8vtI0MfCxgB/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e47f76d5361b65f015996d056bdcaa25001affe576dc2c07b5b0d4fc5101d0c6","last_reissued_at":"2026-07-05T03:51:14.579438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:14.579438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Manifold Clustering and Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Friedrich T. Sommer, Yann LeCun, Yubei Chen, Zengyi Li","submitted_at":"2022-01-24T23:13:37Z","abstract_excerpt":"Given a union of non-linear manifolds, non-linear subspace clustering or manifold clustering aims to cluster data points based on manifold structures and also learn to parameterize each manifold as a linear subspace in a feature space. Deep neural networks have the potential to achieve this goal under highly non-linear settings given their large capacity and flexibility. We argue that achieving manifold clustering with neural networks requires two essential ingredients: a domain-specific constraint that ensures the identification of the manifolds, and a learning algorithm for embedding each ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10000","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/2201.10000/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":"2201.10000","created_at":"2026-07-05T03:51:14.579500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10000v1","created_at":"2026-07-05T03:51:14.579500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10000","created_at":"2026-07-05T03:51:14.579500+00:00"},{"alias_kind":"pith_short_12","alias_value":"4R7XNVJWDNS7","created_at":"2026-07-05T03:51:14.579500+00:00"},{"alias_kind":"pith_short_16","alias_value":"4R7XNVJWDNS7AFMZ","created_at":"2026-07-05T03:51:14.579500+00:00"},{"alias_kind":"pith_short_8","alias_value":"4R7XNVJW","created_at":"2026-07-05T03:51:14.579500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21743","citing_title":"Cohort Organized Learning: Clustering Through Agreement","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05753","citing_title":"Jointly Learning Structured Representations and Stabilized Affinity for Human Motion Segmentation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00718","citing_title":"Learning Coarse-to-Fine Osteoarthritis Representations under Noisy Hierarchical Labels","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU","json":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU.json","graph_json":"https://pith.science/api/pith-number/4R7XNVJWDNS7AFMZNUCWXXFKEU/graph.json","events_json":"https://pith.science/api/pith-number/4R7XNVJWDNS7AFMZNUCWXXFKEU/events.json","paper":"https://pith.science/paper/4R7XNVJW"},"agent_actions":{"view_html":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU","download_json":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU.json","view_paper":"https://pith.science/paper/4R7XNVJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10000&json=true","fetch_graph":"https://pith.science/api/pith-number/4R7XNVJWDNS7AFMZNUCWXXFKEU/graph.json","fetch_events":"https://pith.science/api/pith-number/4R7XNVJWDNS7AFMZNUCWXXFKEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU/action/storage_attestation","attest_author":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU/action/author_attestation","sign_citation":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU/action/citation_signature","submit_replication":"https://pith.science/pith/4R7XNVJWDNS7AFMZNUCWXXFKEU/action/replication_record"}},"created_at":"2026-07-05T03:51:14.579500+00:00","updated_at":"2026-07-05T03:51:14.579500+00:00"}