{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SIPI2QNEEG7D6ABAUH7CHITDNI","short_pith_number":"pith:SIPI2QNE","schema_version":"1.0","canonical_sha256":"921e8d41a421be3f0020a1fe23a2636a0191c3e61ab117b3b6a50f1a481e151d","source":{"kind":"arxiv","id":"2102.00264","version":2},"attestation_state":"computed","paper":{"title":"Atlas Generative Models and Geodesic Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.GT"],"primary_cat":"cs.LG","authors_text":"Jakob Stolberg-Larsen, Stefan Sommer","submitted_at":"2021-01-30T16:35:25Z","abstract_excerpt":"Generative neural networks have a well recognized ability to estimate underlying manifold structure of high dimensional data. However, if a single latent space is used, it is not possible to faithfully represent a manifold with topology different from Euclidean space. In this work we define the general class of Atlas Generative Models (AGMs), models with hybrid discrete-continuous latent space that estimate an atlas on the underlying data manifold together with a partition of unity on the data space. We identify existing examples of models from various popular generative paradigms that fit int"},"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":"2102.00264","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-30T16:35:25Z","cross_cats_sorted":["cs.CV","math.GT"],"title_canon_sha256":"03408c385a8f8def64b4d0176d15e4c94cb042fc1828a681864dec6d8f52d94e","abstract_canon_sha256":"2be38920cd9c60a1d6ada9f5ea30fdd95ccd6e242f5571581f5a16d304c2b3af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:41.236929Z","signature_b64":"u5gDcT2lzUT3ur+QBukSeSvoLmLWdmtrqdWFtMmZ3FqvlGj0EVkcZ2tcTrvP0VTb74zpa/3skgcQ4/dPouohCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921e8d41a421be3f0020a1fe23a2636a0191c3e61ab117b3b6a50f1a481e151d","last_reissued_at":"2026-07-05T04:06:41.236522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:41.236522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Atlas Generative Models and Geodesic Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.GT"],"primary_cat":"cs.LG","authors_text":"Jakob Stolberg-Larsen, Stefan Sommer","submitted_at":"2021-01-30T16:35:25Z","abstract_excerpt":"Generative neural networks have a well recognized ability to estimate underlying manifold structure of high dimensional data. However, if a single latent space is used, it is not possible to faithfully represent a manifold with topology different from Euclidean space. In this work we define the general class of Atlas Generative Models (AGMs), models with hybrid discrete-continuous latent space that estimate an atlas on the underlying data manifold together with a partition of unity on the data space. We identify existing examples of models from various popular generative paradigms that fit int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00264","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/2102.00264/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":"2102.00264","created_at":"2026-07-05T04:06:41.236579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00264v2","created_at":"2026-07-05T04:06:41.236579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00264","created_at":"2026-07-05T04:06:41.236579+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIPI2QNEEG7D","created_at":"2026-07-05T04:06:41.236579+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIPI2QNEEG7D6ABA","created_at":"2026-07-05T04:06:41.236579+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIPI2QNE","created_at":"2026-07-05T04:06:41.236579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI","json":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI.json","graph_json":"https://pith.science/api/pith-number/SIPI2QNEEG7D6ABAUH7CHITDNI/graph.json","events_json":"https://pith.science/api/pith-number/SIPI2QNEEG7D6ABAUH7CHITDNI/events.json","paper":"https://pith.science/paper/SIPI2QNE"},"agent_actions":{"view_html":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI","download_json":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI.json","view_paper":"https://pith.science/paper/SIPI2QNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00264&json=true","fetch_graph":"https://pith.science/api/pith-number/SIPI2QNEEG7D6ABAUH7CHITDNI/graph.json","fetch_events":"https://pith.science/api/pith-number/SIPI2QNEEG7D6ABAUH7CHITDNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI/action/storage_attestation","attest_author":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI/action/author_attestation","sign_citation":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI/action/citation_signature","submit_replication":"https://pith.science/pith/SIPI2QNEEG7D6ABAUH7CHITDNI/action/replication_record"}},"created_at":"2026-07-05T04:06:41.236579+00:00","updated_at":"2026-07-05T04:06:41.236579+00:00"}