{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QPOOOR56M4YDRTFKNZN5NBR5KK","short_pith_number":"pith:QPOOOR56","schema_version":"1.0","canonical_sha256":"83dce747be673038ccaa6e5bd6863d528e430f9ad10b9fad2e03c10fece9363e","source":{"kind":"arxiv","id":"1710.11379","version":3},"attestation_state":"computed","paper":{"title":"Latent Space Oddity: on the Curvature of Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Georgios Arvanitidis, Lars Kai Hansen, S{\\o}ren Hauberg","submitted_at":"2017-10-31T09:10:10Z","abstract_excerpt":"Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear \"generator\" function that maps latent points into the input space. The nonlinearity of the generator imply that the latent space gives a distorted view of the input space. Under mild conditions, we show that this distortion can be characterized by a stochastic Riemannian metric, and demonstrate that distances and interpolants are significantly improved under this metric. This in turn improves probability distributions, sampling algorithms and clustering in th"},"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":"1710.11379","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-31T09:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"a29a6031bcb1f96c1b3ad97d8fa3e429434445e63fd11f756b83e4021513d9fb","abstract_canon_sha256":"94d88f8016e1c2c8b7639c560241b69dd7fbf19a50fe9a363343323ce14e49ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:51.954424Z","signature_b64":"3g/r0RV7vvLru3mq922ssqVzRMHqlg0D14ZoRrykQ8ywECg497Wet+K39Hv59DtlVbxUgNyB+VDeyUpyzH4NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83dce747be673038ccaa6e5bd6863d528e430f9ad10b9fad2e03c10fece9363e","last_reissued_at":"2026-07-05T03:39:51.954013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:51.954013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Space Oddity: on the Curvature of Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Georgios Arvanitidis, Lars Kai Hansen, S{\\o}ren Hauberg","submitted_at":"2017-10-31T09:10:10Z","abstract_excerpt":"Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear \"generator\" function that maps latent points into the input space. The nonlinearity of the generator imply that the latent space gives a distorted view of the input space. Under mild conditions, we show that this distortion can be characterized by a stochastic Riemannian metric, and demonstrate that distances and interpolants are significantly improved under this metric. This in turn improves probability distributions, sampling algorithms and clustering in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11379","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/1710.11379/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":"1710.11379","created_at":"2026-07-05T03:39:51.954059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.11379v3","created_at":"2026-07-05T03:39:51.954059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11379","created_at":"2026-07-05T03:39:51.954059+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPOOOR56M4YD","created_at":"2026-07-05T03:39:51.954059+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPOOOR56M4YDRTFK","created_at":"2026-07-05T03:39:51.954059+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPOOOR56","created_at":"2026-07-05T03:39:51.954059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07047","citing_title":"Riemannian Geometry for Pre-trained Language Model Embeddings","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01275","citing_title":"eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12520","citing_title":"Charting the emergent low-dimensional manifold of quantum materials","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18587","citing_title":"PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30248","citing_title":"Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11221","citing_title":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24985","citing_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18587","citing_title":"PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK","json":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK.json","graph_json":"https://pith.science/api/pith-number/QPOOOR56M4YDRTFKNZN5NBR5KK/graph.json","events_json":"https://pith.science/api/pith-number/QPOOOR56M4YDRTFKNZN5NBR5KK/events.json","paper":"https://pith.science/paper/QPOOOR56"},"agent_actions":{"view_html":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK","download_json":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK.json","view_paper":"https://pith.science/paper/QPOOOR56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.11379&json=true","fetch_graph":"https://pith.science/api/pith-number/QPOOOR56M4YDRTFKNZN5NBR5KK/graph.json","fetch_events":"https://pith.science/api/pith-number/QPOOOR56M4YDRTFKNZN5NBR5KK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK/action/storage_attestation","attest_author":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK/action/author_attestation","sign_citation":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK/action/citation_signature","submit_replication":"https://pith.science/pith/QPOOOR56M4YDRTFKNZN5NBR5KK/action/replication_record"}},"created_at":"2026-07-05T03:39:51.954059+00:00","updated_at":"2026-07-05T03:39:51.954059+00:00"}