{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SLNE6EOKFNPABOI34HHJR7ORSG","short_pith_number":"pith:SLNE6EOK","schema_version":"1.0","canonical_sha256":"92da4f11ca2b5e00b91be1ce98fdd1918f9c20a9409b91032325bc2e6ed2faed","source":{"kind":"arxiv","id":"2002.04881","version":3},"attestation_state":"computed","paper":{"title":"Learning Flat Latent Manifolds with VAEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexej Klushyn, Francesco Ferroni, Justin Bayer, Nutan Chen, Patrick van der Smagt","submitted_at":"2020-02-12T09:54:52Z","abstract_excerpt":"Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact latent space. Prevalent is the use of the Euclidean metric, which has the drawback of ignoring information about similarity of data stored in the decoder, as captured by the framework of Riemannian geometry. We propose an extension to the framework of variational auto-encoders allows learning flat latent manifolds, where the Euclidean metric is a proxy for the s"},"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":"2002.04881","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-12T09:54:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c1efc69f1dadbb00ea1f36f0804d46dda02c43c260734f1de8afcc316dfc28f","abstract_canon_sha256":"010d04fdb18d29977734b03f97fc578fcb4867a33227ffd41940521e6c4d956e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:39.761563Z","signature_b64":"id5S13We8lpZr9sJpru3VxcVxW3ZWprwdyED5TaGbtZ/vWKr7p496IgxG7VRm40Q5Ogd+0FRrWtzGkwnAb5dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92da4f11ca2b5e00b91be1ce98fdd1918f9c20a9409b91032325bc2e6ed2faed","last_reissued_at":"2026-07-05T01:26:39.761138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:39.761138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Flat Latent Manifolds with VAEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexej Klushyn, Francesco Ferroni, Justin Bayer, Nutan Chen, Patrick van der Smagt","submitted_at":"2020-02-12T09:54:52Z","abstract_excerpt":"Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact latent space. Prevalent is the use of the Euclidean metric, which has the drawback of ignoring information about similarity of data stored in the decoder, as captured by the framework of Riemannian geometry. We propose an extension to the framework of variational auto-encoders allows learning flat latent manifolds, where the Euclidean metric is a proxy for the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04881","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/2002.04881/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":"2002.04881","created_at":"2026-07-05T01:26:39.761193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04881v3","created_at":"2026-07-05T01:26:39.761193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04881","created_at":"2026-07-05T01:26:39.761193+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLNE6EOKFNPA","created_at":"2026-07-05T01:26:39.761193+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLNE6EOKFNPABOI3","created_at":"2026-07-05T01:26:39.761193+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLNE6EOK","created_at":"2026-07-05T01:26:39.761193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06701","citing_title":"Bi-Lipschitz Autoencoder With Injectivity Guarantee","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG","json":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG.json","graph_json":"https://pith.science/api/pith-number/SLNE6EOKFNPABOI34HHJR7ORSG/graph.json","events_json":"https://pith.science/api/pith-number/SLNE6EOKFNPABOI34HHJR7ORSG/events.json","paper":"https://pith.science/paper/SLNE6EOK"},"agent_actions":{"view_html":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG","download_json":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG.json","view_paper":"https://pith.science/paper/SLNE6EOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04881&json=true","fetch_graph":"https://pith.science/api/pith-number/SLNE6EOKFNPABOI34HHJR7ORSG/graph.json","fetch_events":"https://pith.science/api/pith-number/SLNE6EOKFNPABOI34HHJR7ORSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG/action/storage_attestation","attest_author":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG/action/author_attestation","sign_citation":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG/action/citation_signature","submit_replication":"https://pith.science/pith/SLNE6EOKFNPABOI34HHJR7ORSG/action/replication_record"}},"created_at":"2026-07-05T01:26:39.761193+00:00","updated_at":"2026-07-05T01:26:39.761193+00:00"}