{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4VG7URFKMVM4EY7XL4DQZVAGMV","short_pith_number":"pith:4VG7URFK","schema_version":"1.0","canonical_sha256":"e54dfa44aa6559c263f75f070cd406655fc3474c7ee0c67ab07de5d934e31723","source":{"kind":"arxiv","id":"1807.04689","version":1},"attestation_state":"computed","paper":{"title":"Explorations in Homeomorphic Variational Auto-Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Falorsi, Maurice Weiler, Nicola De Cao, Patrick Forr\\'e, Pim de Haan, Taco S. Cohen, Tim R. Davidson","submitted_at":"2018-07-12T15:55:55Z","abstract_excerpt":"The manifold hypothesis states that many kinds of high-dimensional data are concentrated near a low-dimensional manifold. If the topology of this data manifold is non-trivial, a continuous encoder network cannot embed it in a one-to-one manner without creating holes of low density in the latent space. This is at odds with the Gaussian prior assumption typically made in Variational Auto-Encoders (VAEs), because the density of a Gaussian concentrates near a blob-like manifold.\n  In this paper we investigate the use of manifold-valued latent variables. Specifically, we focus on the important case"},"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":"1807.04689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T15:55:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"575a1c3dd4c5b88d5c81f46961e9e08062bb8d7a14879c52e3631dd37d46d6ca","abstract_canon_sha256":"48440c44a9cdbd6a663ee1ba90939408c9a46ffde8691df9165de4949d3d9ea4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:52.786501Z","signature_b64":"eK4RFJiKWZn3fR0GTb4IgwUuMGE6HUncCzEEgkabM+RsAdiaNEebrnzyIL6NBTm6kj/phi4A7ZcaWGB7S0k5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e54dfa44aa6559c263f75f070cd406655fc3474c7ee0c67ab07de5d934e31723","last_reissued_at":"2026-05-18T00:10:52.785957Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:52.785957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explorations in Homeomorphic Variational Auto-Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Falorsi, Maurice Weiler, Nicola De Cao, Patrick Forr\\'e, Pim de Haan, Taco S. Cohen, Tim R. Davidson","submitted_at":"2018-07-12T15:55:55Z","abstract_excerpt":"The manifold hypothesis states that many kinds of high-dimensional data are concentrated near a low-dimensional manifold. If the topology of this data manifold is non-trivial, a continuous encoder network cannot embed it in a one-to-one manner without creating holes of low density in the latent space. This is at odds with the Gaussian prior assumption typically made in Variational Auto-Encoders (VAEs), because the density of a Gaussian concentrates near a blob-like manifold.\n  In this paper we investigate the use of manifold-valued latent variables. Specifically, we focus on the important case"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04689","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":"1807.04689","created_at":"2026-05-18T00:10:52.786044+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04689v1","created_at":"2026-05-18T00:10:52.786044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04689","created_at":"2026-05-18T00:10:52.786044+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VG7URFKMVM4","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VG7URFKMVM4EY7X","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VG7URFK","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18606","citing_title":"Physics-Aligned Canonical Equivariant Fourier Neural Operator under Symmetry-Induced Shifts","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28122","citing_title":"Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06479","citing_title":"Risk-Controlled Post-Processing of Decision Policies","ref_index":288,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV","json":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV.json","graph_json":"https://pith.science/api/pith-number/4VG7URFKMVM4EY7XL4DQZVAGMV/graph.json","events_json":"https://pith.science/api/pith-number/4VG7URFKMVM4EY7XL4DQZVAGMV/events.json","paper":"https://pith.science/paper/4VG7URFK"},"agent_actions":{"view_html":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV","download_json":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV.json","view_paper":"https://pith.science/paper/4VG7URFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04689&json=true","fetch_graph":"https://pith.science/api/pith-number/4VG7URFKMVM4EY7XL4DQZVAGMV/graph.json","fetch_events":"https://pith.science/api/pith-number/4VG7URFKMVM4EY7XL4DQZVAGMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV/action/storage_attestation","attest_author":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV/action/author_attestation","sign_citation":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV/action/citation_signature","submit_replication":"https://pith.science/pith/4VG7URFKMVM4EY7XL4DQZVAGMV/action/replication_record"}},"created_at":"2026-05-18T00:10:52.786044+00:00","updated_at":"2026-05-18T00:10:52.786044+00:00"}