{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RC5OEUJRCLYKRDTGZ36VX226HR","short_pith_number":"pith:RC5OEUJR","schema_version":"1.0","canonical_sha256":"88bae2513112f0a88e66cefd5beb5e3c6897bc1b240ac19b2e5afbf952932dc0","source":{"kind":"arxiv","id":"2410.10137","version":5},"attestation_state":"computed","paper":{"title":"Variational autoencoders with latent high-dimensional steady geometric flows for dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DG","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gracyk","submitted_at":"2024-10-14T04:07:45Z","abstract_excerpt":"We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework such that manifold geometries, subject to our geometric flow, embedded in Euclidean space are learned in the intermediary latent space developed by encoders and decoders. By tailoring the geometric flow in which the latent space evolves, we induce latent geometric properties of our choosing, which are reflected in empirical performance. We reformulate the t"},"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":"2410.10137","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T04:07:45Z","cross_cats_sorted":["math.DG","stat.CO","stat.ML"],"title_canon_sha256":"012c7b007f15ccbc499d040d960fa555640df56e1dfbaa19e3e2c1fa014f5984","abstract_canon_sha256":"001c2a5a0b4f8427e2faf43dd7c98a469e2f79184a67758e76d5fb21ffaa7e96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:46.826544Z","signature_b64":"wzQTE7nJ6dCekiVrkMR8jQD9AcAGT/Au0H5yY4kE8X03ljyeBezDSbhBCoJSJNGA5jNj9RfZQUl51EPM4gUmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88bae2513112f0a88e66cefd5beb5e3c6897bc1b240ac19b2e5afbf952932dc0","last_reissued_at":"2026-06-19T16:09:46.826073Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:46.826073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational autoencoders with latent high-dimensional steady geometric flows for dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DG","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gracyk","submitted_at":"2024-10-14T04:07:45Z","abstract_excerpt":"We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework such that manifold geometries, subject to our geometric flow, embedded in Euclidean space are learned in the intermediary latent space developed by encoders and decoders. By tailoring the geometric flow in which the latent space evolves, we induce latent geometric properties of our choosing, which are reflected in empirical performance. We reformulate the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10137","kind":"arxiv","version":5},"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/2410.10137/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":"2410.10137","created_at":"2026-06-19T16:09:46.826131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10137v5","created_at":"2026-06-19T16:09:46.826131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10137","created_at":"2026-06-19T16:09:46.826131+00:00"},{"alias_kind":"pith_short_12","alias_value":"RC5OEUJRCLYK","created_at":"2026-06-19T16:09:46.826131+00:00"},{"alias_kind":"pith_short_16","alias_value":"RC5OEUJRCLYKRDTG","created_at":"2026-06-19T16:09:46.826131+00:00"},{"alias_kind":"pith_short_8","alias_value":"RC5OEUJR","created_at":"2026-06-19T16:09:46.826131+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/RC5OEUJRCLYKRDTGZ36VX226HR","json":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR.json","graph_json":"https://pith.science/api/pith-number/RC5OEUJRCLYKRDTGZ36VX226HR/graph.json","events_json":"https://pith.science/api/pith-number/RC5OEUJRCLYKRDTGZ36VX226HR/events.json","paper":"https://pith.science/paper/RC5OEUJR"},"agent_actions":{"view_html":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR","download_json":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR.json","view_paper":"https://pith.science/paper/RC5OEUJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10137&json=true","fetch_graph":"https://pith.science/api/pith-number/RC5OEUJRCLYKRDTGZ36VX226HR/graph.json","fetch_events":"https://pith.science/api/pith-number/RC5OEUJRCLYKRDTGZ36VX226HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR/action/storage_attestation","attest_author":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR/action/author_attestation","sign_citation":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR/action/citation_signature","submit_replication":"https://pith.science/pith/RC5OEUJRCLYKRDTGZ36VX226HR/action/replication_record"}},"created_at":"2026-06-19T16:09:46.826131+00:00","updated_at":"2026-06-19T16:09:46.826131+00:00"}