{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:U3RKLUWUDR7B7KYVEYVOSXCYNL","short_pith_number":"pith:U3RKLUWU","schema_version":"1.0","canonical_sha256":"a6e2a5d2d41c7e1fab15262ae95c586ae34ebf502846f2362df7015faef1154d","source":{"kind":"arxiv","id":"2002.09779","version":2},"attestation_state":"computed","paper":{"title":"Stochasticity in Neural ODEs: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandra Volokhova, Dmitry Vetrov, Viktor Oganesyan","submitted_at":"2020-02-22T22:12:56Z","abstract_excerpt":"Stochastic regularization of neural networks (e.g. dropout) is a wide-spread technique in deep learning that allows for better generalization. Despite its success, continuous-time models, such as neural ordinary differential equation (ODE), usually rely on a completely deterministic feed-forward operation. This work provides an empirical study of stochastically regularized neural ODE on several image-classification tasks (CIFAR-10, CIFAR-100, TinyImageNet). Building upon the formalism of stochastic differential equations (SDEs), we demonstrate that neural SDE is able to outperform its determin"},"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":"2002.09779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-22T22:12:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2f92c8207a80e491503f9e2b35711f86c1b311e17af6e097283d6c98165682b3","abstract_canon_sha256":"153908d095861b6ae33b936bad357590dd9877c4148c0637a940976e50110e50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:43.546290Z","signature_b64":"MQNkKuuGcAuUfFuzgF6PQXzWTCi00Z2HDwiFQBRVznRGl0DU6ITEtxZOdW+JNguMYBQbCLTfKpQKU53yk2nfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6e2a5d2d41c7e1fab15262ae95c586ae34ebf502846f2362df7015faef1154d","last_reissued_at":"2026-07-05T01:13:43.545824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:43.545824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochasticity in Neural ODEs: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandra Volokhova, Dmitry Vetrov, Viktor Oganesyan","submitted_at":"2020-02-22T22:12:56Z","abstract_excerpt":"Stochastic regularization of neural networks (e.g. dropout) is a wide-spread technique in deep learning that allows for better generalization. Despite its success, continuous-time models, such as neural ordinary differential equation (ODE), usually rely on a completely deterministic feed-forward operation. This work provides an empirical study of stochastically regularized neural ODE on several image-classification tasks (CIFAR-10, CIFAR-100, TinyImageNet). Building upon the formalism of stochastic differential equations (SDEs), we demonstrate that neural SDE is able to outperform its determin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09779","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/2002.09779/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":"2002.09779","created_at":"2026-07-05T01:13:43.545881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09779v2","created_at":"2026-07-05T01:13:43.545881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09779","created_at":"2026-07-05T01:13:43.545881+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3RKLUWUDR7B","created_at":"2026-07-05T01:13:43.545881+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3RKLUWUDR7B7KYV","created_at":"2026-07-05T01:13:43.545881+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3RKLUWU","created_at":"2026-07-05T01:13:43.545881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06686","citing_title":"Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL","json":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL.json","graph_json":"https://pith.science/api/pith-number/U3RKLUWUDR7B7KYVEYVOSXCYNL/graph.json","events_json":"https://pith.science/api/pith-number/U3RKLUWUDR7B7KYVEYVOSXCYNL/events.json","paper":"https://pith.science/paper/U3RKLUWU"},"agent_actions":{"view_html":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL","download_json":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL.json","view_paper":"https://pith.science/paper/U3RKLUWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09779&json=true","fetch_graph":"https://pith.science/api/pith-number/U3RKLUWUDR7B7KYVEYVOSXCYNL/graph.json","fetch_events":"https://pith.science/api/pith-number/U3RKLUWUDR7B7KYVEYVOSXCYNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL/action/storage_attestation","attest_author":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL/action/author_attestation","sign_citation":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL/action/citation_signature","submit_replication":"https://pith.science/pith/U3RKLUWUDR7B7KYVEYVOSXCYNL/action/replication_record"}},"created_at":"2026-07-05T01:13:43.545881+00:00","updated_at":"2026-07-05T01:13:43.545881+00:00"}