{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FT2WMB4ITXLDTDJ74VSU7VOZBG","short_pith_number":"pith:FT2WMB4I","schema_version":"1.0","canonical_sha256":"2cf56607889dd6398d3fe5654fd5d90987369212c5993eef74ffe8488b98f01b","source":{"kind":"arxiv","id":"2008.00565","version":1},"attestation_state":"computed","paper":{"title":"Geometrically Enriched Latent Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Georgios Arvanitidis, S{\\o}ren Hauberg","submitted_at":"2020-08-02T20:57:58Z","abstract_excerpt":"A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space. Instead, we consider the ambient space to be a Riemannian manifold, which allows for encoding domain knowledge through the associated Riemannian metric. Shortest paths can then be defined accordingly in the latent space to both follow the learned manifold and respect the ambient geometry. Through careful design of the ambient metric we can ensure that shortest paths are well-behaved even for deterministic generators that otherwise would exhibit a misleading bias. Experimenta"},"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":"2008.00565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-08-02T20:57:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2cc1b9c52941698876072137fe583fbe9fee65f5824ea852dea06f46c5f9d868","abstract_canon_sha256":"4db42e8e5cb84e3f9c12a1c8a3b2fdcab6ba2de8c7d0cde040fdcfa0e5b22b06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:08.894477Z","signature_b64":"aRMwHtbzAXsTzHWfKQOJSiA3WpFLsBamuf5mRWqV5NSCaa2xyrgNjykoNZZfXgwZEwdnFZvDCXSBqkwgAigvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf56607889dd6398d3fe5654fd5d90987369212c5993eef74ffe8488b98f01b","last_reissued_at":"2026-07-05T01:24:08.894047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:08.894047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometrically Enriched Latent Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Georgios Arvanitidis, S{\\o}ren Hauberg","submitted_at":"2020-08-02T20:57:58Z","abstract_excerpt":"A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space. Instead, we consider the ambient space to be a Riemannian manifold, which allows for encoding domain knowledge through the associated Riemannian metric. Shortest paths can then be defined accordingly in the latent space to both follow the learned manifold and respect the ambient geometry. Through careful design of the ambient metric we can ensure that shortest paths are well-behaved even for deterministic generators that otherwise would exhibit a misleading bias. Experimenta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00565","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/2008.00565/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":"2008.00565","created_at":"2026-07-05T01:24:08.894109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.00565v1","created_at":"2026-07-05T01:24:08.894109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00565","created_at":"2026-07-05T01:24:08.894109+00:00"},{"alias_kind":"pith_short_12","alias_value":"FT2WMB4ITXLD","created_at":"2026-07-05T01:24:08.894109+00:00"},{"alias_kind":"pith_short_16","alias_value":"FT2WMB4ITXLDTDJ7","created_at":"2026-07-05T01:24:08.894109+00:00"},{"alias_kind":"pith_short_8","alias_value":"FT2WMB4I","created_at":"2026-07-05T01:24:08.894109+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":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG","json":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG.json","graph_json":"https://pith.science/api/pith-number/FT2WMB4ITXLDTDJ74VSU7VOZBG/graph.json","events_json":"https://pith.science/api/pith-number/FT2WMB4ITXLDTDJ74VSU7VOZBG/events.json","paper":"https://pith.science/paper/FT2WMB4I"},"agent_actions":{"view_html":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG","download_json":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG.json","view_paper":"https://pith.science/paper/FT2WMB4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.00565&json=true","fetch_graph":"https://pith.science/api/pith-number/FT2WMB4ITXLDTDJ74VSU7VOZBG/graph.json","fetch_events":"https://pith.science/api/pith-number/FT2WMB4ITXLDTDJ74VSU7VOZBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG/action/storage_attestation","attest_author":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG/action/author_attestation","sign_citation":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG/action/citation_signature","submit_replication":"https://pith.science/pith/FT2WMB4ITXLDTDJ74VSU7VOZBG/action/replication_record"}},"created_at":"2026-07-05T01:24:08.894109+00:00","updated_at":"2026-07-05T01:24:08.894109+00:00"}