{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BLOSYKK3T43M64WIXMKAGNOUX5","short_pith_number":"pith:BLOSYKK3","schema_version":"1.0","canonical_sha256":"0add2c295b9f36cf72c8bb140335d4bf6040a553a38c35084a419f03e6ebc965","source":{"kind":"arxiv","id":"2209.07370","version":2},"attestation_state":"computed","paper":{"title":"A Geometric Perspective on Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Cl\\'ement Chadebec, St\\'ephanie Allassonni\\`ere","submitted_at":"2022-09-15T15:32:43Z","abstract_excerpt":"This paper introduces a new interpretation of the Variational Autoencoder framework by taking a fully geometric point of view. We argue that vanilla VAE models unveil naturally a Riemannian structure in their latent space and that taking into consideration those geometrical aspects can lead to better interpolations and an improved generation procedure. This new proposed sampling method consists in sampling from the uniform distribution deriving intrinsically from the learned Riemannian latent space and we show that using this scheme can make a vanilla VAE competitive and even better than more "},"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":"2209.07370","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-15T15:32:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c7f58778f095f799f3cdaf6102fc0ce4adc176772c0904901127ebc2045fd473","abstract_canon_sha256":"7e4cae19cdee26f0c6a656f7581bdc15232c4493a2c89fa4fe7302aa31b1a19d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:53.271037Z","signature_b64":"NG08ZCTibe9Gz8Sx1o8I6/UjGvvNC8nb/f//DxY9u9YawZtJgE6WwmdaSM/j1FzAzYOPkzQeXFhA1FTzI4BpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0add2c295b9f36cf72c8bb140335d4bf6040a553a38c35084a419f03e6ebc965","last_reissued_at":"2026-07-05T05:12:53.270556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:53.270556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Geometric Perspective on Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Cl\\'ement Chadebec, St\\'ephanie Allassonni\\`ere","submitted_at":"2022-09-15T15:32:43Z","abstract_excerpt":"This paper introduces a new interpretation of the Variational Autoencoder framework by taking a fully geometric point of view. We argue that vanilla VAE models unveil naturally a Riemannian structure in their latent space and that taking into consideration those geometrical aspects can lead to better interpolations and an improved generation procedure. This new proposed sampling method consists in sampling from the uniform distribution deriving intrinsically from the learned Riemannian latent space and we show that using this scheme can make a vanilla VAE competitive and even better than more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07370","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.07370/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":"2209.07370","created_at":"2026-07-05T05:12:53.270612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07370v2","created_at":"2026-07-05T05:12:53.270612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07370","created_at":"2026-07-05T05:12:53.270612+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLOSYKK3T43M","created_at":"2026-07-05T05:12:53.270612+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLOSYKK3T43M64WI","created_at":"2026-07-05T05:12:53.270612+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLOSYKK3","created_at":"2026-07-05T05:12:53.270612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09679","citing_title":"Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5","json":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5.json","graph_json":"https://pith.science/api/pith-number/BLOSYKK3T43M64WIXMKAGNOUX5/graph.json","events_json":"https://pith.science/api/pith-number/BLOSYKK3T43M64WIXMKAGNOUX5/events.json","paper":"https://pith.science/paper/BLOSYKK3"},"agent_actions":{"view_html":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5","download_json":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5.json","view_paper":"https://pith.science/paper/BLOSYKK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07370&json=true","fetch_graph":"https://pith.science/api/pith-number/BLOSYKK3T43M64WIXMKAGNOUX5/graph.json","fetch_events":"https://pith.science/api/pith-number/BLOSYKK3T43M64WIXMKAGNOUX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5/action/storage_attestation","attest_author":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5/action/author_attestation","sign_citation":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5/action/citation_signature","submit_replication":"https://pith.science/pith/BLOSYKK3T43M64WIXMKAGNOUX5/action/replication_record"}},"created_at":"2026-07-05T05:12:53.270612+00:00","updated_at":"2026-07-05T05:12:53.270612+00:00"}