{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BLNZLKYTMQFAPWGPLXBNMGOVK5","short_pith_number":"pith:BLNZLKYT","schema_version":"1.0","canonical_sha256":"0adb95ab13640a07d8cf5dc2d619d55775c2ef7361a951e4e283d891d47f9f85","source":{"kind":"arxiv","id":"1804.00891","version":3},"attestation_state":"computed","paper":{"title":"Hyperspherical Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jakub M. Tomczak, Luca Falorsi, Nicola De Cao, Thomas Kipf, Tim R. Davidson","submitted_at":"2018-04-03T09:57:26Z","abstract_excerpt":"The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or $\\mathcal{S}$-VAE, is mo"},"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":"1804.00891","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-03T09:57:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3883f0fa0581a067712725781fc78d44b28c2da98fff436d48f36f868309a18","abstract_canon_sha256":"4ebcf3b3375de90162c5ce94d8f16947dfc993629954ab625a1389ac75daf21c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:57.467302Z","signature_b64":"4rSqrj5c93t936EyI4Z6Quhoqf9pGkCknZ2I4fMKLlBbiIH8In20G+37tv+PQAgX44gpdwAfVeCvB6kJcKnECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0adb95ab13640a07d8cf5dc2d619d55775c2ef7361a951e4e283d891d47f9f85","last_reissued_at":"2026-07-05T05:00:57.466898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:57.466898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperspherical Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jakub M. Tomczak, Luca Falorsi, Nicola De Cao, Thomas Kipf, Tim R. Davidson","submitted_at":"2018-04-03T09:57:26Z","abstract_excerpt":"The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or $\\mathcal{S}$-VAE, is mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00891","kind":"arxiv","version":3},"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/1804.00891/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":"1804.00891","created_at":"2026-07-05T05:00:57.466957+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00891v3","created_at":"2026-07-05T05:00:57.466957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00891","created_at":"2026-07-05T05:00:57.466957+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLNZLKYTMQFA","created_at":"2026-07-05T05:00:57.466957+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLNZLKYTMQFAPWGP","created_at":"2026-07-05T05:00:57.466957+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLNZLKYT","created_at":"2026-07-05T05:00:57.466957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13517","citing_title":"ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12764","citing_title":"Yield Curves Dynamics Using Variational Autoencoders Under No-arbitrage","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15193","citing_title":"Aligning Latent Geometry for Spherical Flow Matching in Image Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00233","citing_title":"Density Evolution: A Multiscale View of Density Estimation","ref_index":212,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19148","citing_title":"Fast Computation of Free-Support Wasserstein Medians","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20681","citing_title":"Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14056","citing_title":"Radial Compensation: Fixing Radius Distortion in Chart-Based Generative Models on Riemannian Manifolds","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13517","citing_title":"ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12764","citing_title":"Yield Curves Dynamics Using Variational Autoencoders Under No-arbitrage","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10993","citing_title":"ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25030","citing_title":"Rectified Fisher-Bingham Model for Compositional Data with Zeros","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23540","citing_title":"Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09087","citing_title":"DIAURec: Dual-Intent Space Representation Optimization for Recommendation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08001","citing_title":"Scale selection for geometric medians on product manifolds","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00363","citing_title":"Profile Likelihood Inference for Anisotropic Hyperbolic Wrapped Normal Models on Hyperbolic Space","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03266","citing_title":"Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5","json":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5.json","graph_json":"https://pith.science/api/pith-number/BLNZLKYTMQFAPWGPLXBNMGOVK5/graph.json","events_json":"https://pith.science/api/pith-number/BLNZLKYTMQFAPWGPLXBNMGOVK5/events.json","paper":"https://pith.science/paper/BLNZLKYT"},"agent_actions":{"view_html":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5","download_json":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5.json","view_paper":"https://pith.science/paper/BLNZLKYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00891&json=true","fetch_graph":"https://pith.science/api/pith-number/BLNZLKYTMQFAPWGPLXBNMGOVK5/graph.json","fetch_events":"https://pith.science/api/pith-number/BLNZLKYTMQFAPWGPLXBNMGOVK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5/action/storage_attestation","attest_author":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5/action/author_attestation","sign_citation":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5/action/citation_signature","submit_replication":"https://pith.science/pith/BLNZLKYTMQFAPWGPLXBNMGOVK5/action/replication_record"}},"created_at":"2026-07-05T05:00:57.466957+00:00","updated_at":"2026-07-05T05:00:57.466957+00:00"}