{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CBNKCAUGLDHH4VSBOOSZE2BX5V","short_pith_number":"pith:CBNKCAUG","schema_version":"1.0","canonical_sha256":"105aa1028658ce7e564173a5926837ed4514d72a5280c1597dbe98ff99c84720","source":{"kind":"arxiv","id":"1905.09883","version":2},"attestation_state":"computed","paper":{"title":"Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Belinda Tzen, Maxim Raginsky","submitted_at":"2019-05-23T19:30:16Z","abstract_excerpt":"In deep latent Gaussian models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlinear map, such as a feedforward neural net, and add a small independent Gaussian perturbation. This work considers the diffusion limit of such models, where the number of layers tends to infinity, while the step size and the noise variance tend to zero. The limiting latent object is an It\\^o diffusion process that solves a stochastic differential equation (SDE) whose drift and diffusion coefficient are implemented by "},"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":"1905.09883","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T19:30:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4222db94c84519c7d79e48867b0bf9d0cdbd72b09f2363476deaa60fb5f5b12","abstract_canon_sha256":"2ad8101dcdb6790ee9605ece485c87fd33f980b05f2eed18df7c13537b814115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:04.956585Z","signature_b64":"4O79U0RAk5aE2OEJHck5bfpZQ7tSTYnQF2ro7Bwmn1M2TCK045RANK537fsRHulmIRKtKDzHXhk2U5+FRoCRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105aa1028658ce7e564173a5926837ed4514d72a5280c1597dbe98ff99c84720","last_reissued_at":"2026-07-05T00:15:04.956073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:04.956073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Belinda Tzen, Maxim Raginsky","submitted_at":"2019-05-23T19:30:16Z","abstract_excerpt":"In deep latent Gaussian models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlinear map, such as a feedforward neural net, and add a small independent Gaussian perturbation. This work considers the diffusion limit of such models, where the number of layers tends to infinity, while the step size and the noise variance tend to zero. The limiting latent object is an It\\^o diffusion process that solves a stochastic differential equation (SDE) whose drift and diffusion coefficient are implemented by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09883","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/1905.09883/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":"1905.09883","created_at":"2026-07-05T00:15:04.956121+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09883v2","created_at":"2026-07-05T00:15:04.956121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09883","created_at":"2026-07-05T00:15:04.956121+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBNKCAUGLDHH","created_at":"2026-07-05T00:15:04.956121+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBNKCAUGLDHH4VSB","created_at":"2026-07-05T00:15:04.956121+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBNKCAUG","created_at":"2026-07-05T00:15:04.956121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11988","citing_title":"What Uncertainties Do We Need for Dynamical Systems?","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11138","citing_title":"First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06094","citing_title":"Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04335","citing_title":"Policy Gradient for Continuous-Time Robust Markov Decision Processes","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01894","citing_title":"Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28880","citing_title":"Towards Continuous-time Causal Foundation Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13228","citing_title":"Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05482","citing_title":"Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17129","citing_title":"DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21860","citing_title":"Pathwise Learning of Stochastic Dynamical Systems with Partial Observations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22564","citing_title":"MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2310.05737","citing_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11007","citing_title":"The Transformer as a Polar State Estimator","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10934","citing_title":"Variational Inference for L\\'evy Process-Driven SDEs via Neural Tilting","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10687","citing_title":"The finite expression method for turbulent dynamics with high-order moment recovery","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05606","citing_title":"Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22208","citing_title":"Finite Expression Method with TranNet-based Function Learning for High-Dimensional Partial Differential Equations","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10414","citing_title":"Neural Stochastic Processes for Satellite Precipitation Refinement","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02303","citing_title":"Imagen Video: High Definition Video Generation with Diffusion Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V","json":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V.json","graph_json":"https://pith.science/api/pith-number/CBNKCAUGLDHH4VSBOOSZE2BX5V/graph.json","events_json":"https://pith.science/api/pith-number/CBNKCAUGLDHH4VSBOOSZE2BX5V/events.json","paper":"https://pith.science/paper/CBNKCAUG"},"agent_actions":{"view_html":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V","download_json":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V.json","view_paper":"https://pith.science/paper/CBNKCAUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09883&json=true","fetch_graph":"https://pith.science/api/pith-number/CBNKCAUGLDHH4VSBOOSZE2BX5V/graph.json","fetch_events":"https://pith.science/api/pith-number/CBNKCAUGLDHH4VSBOOSZE2BX5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V/action/storage_attestation","attest_author":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V/action/author_attestation","sign_citation":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V/action/citation_signature","submit_replication":"https://pith.science/pith/CBNKCAUGLDHH4VSBOOSZE2BX5V/action/replication_record"}},"created_at":"2026-07-05T00:15:04.956121+00:00","updated_at":"2026-07-05T00:15:04.956121+00:00"}