{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:X5JGGPK5UFJFZVMDGHDIJRCPY7","short_pith_number":"pith:X5JGGPK5","schema_version":"1.0","canonical_sha256":"bf52633d5da1525cd58331c684c44fc7c79143161e1cd64d1210a74725aff465","source":{"kind":"arxiv","id":"2112.12707","version":1},"attestation_state":"computed","paper":{"title":"Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"P.K. Srijith, Srinivas Anumasa","submitted_at":"2021-12-23T16:56:10Z","abstract_excerpt":"Neural ordinary differential equations (NODE) have been proposed as a continuous depth generalization to popular deep learning models such as Residual networks (ResNets). They provide parameter efficiency and automate the model selection process in deep learning models to some extent. However, they lack the much-required uncertainty modelling and robustness capabilities which are crucial for their use in several real-world applications such as autonomous driving and healthcare. We propose a novel and unique approach to model uncertainty in NODE by considering a distribution over the end-time $"},"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":"2112.12707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-23T16:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"111a34ea892173f826686ee98e0bccd21ba3e95b1437a733a1fbbcd509cc96a8","abstract_canon_sha256":"da8943ed3008537e40b6c85b45c774526439b44790148c0b4cbacbe65f4f7acc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:30.399456Z","signature_b64":"4xfuUO+WVvApGoP1mnQrKAcRtWH+5SAUgYHB2YXBdm6fplNEwjSwVkothaxT/Zk5OKMHp3pM+ArtNH5IAONwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf52633d5da1525cd58331c684c44fc7c79143161e1cd64d1210a74725aff465","last_reissued_at":"2026-07-05T03:43:30.399039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:30.399039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"P.K. Srijith, Srinivas Anumasa","submitted_at":"2021-12-23T16:56:10Z","abstract_excerpt":"Neural ordinary differential equations (NODE) have been proposed as a continuous depth generalization to popular deep learning models such as Residual networks (ResNets). They provide parameter efficiency and automate the model selection process in deep learning models to some extent. However, they lack the much-required uncertainty modelling and robustness capabilities which are crucial for their use in several real-world applications such as autonomous driving and healthcare. We propose a novel and unique approach to model uncertainty in NODE by considering a distribution over the end-time $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12707","kind":"arxiv","version":1},"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/2112.12707/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":"2112.12707","created_at":"2026-07-05T03:43:30.399094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12707v1","created_at":"2026-07-05T03:43:30.399094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12707","created_at":"2026-07-05T03:43:30.399094+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5JGGPK5UFJF","created_at":"2026-07-05T03:43:30.399094+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5JGGPK5UFJFZVMD","created_at":"2026-07-05T03:43:30.399094+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5JGGPK5","created_at":"2026-07-05T03:43:30.399094+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/X5JGGPK5UFJFZVMDGHDIJRCPY7","json":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7.json","graph_json":"https://pith.science/api/pith-number/X5JGGPK5UFJFZVMDGHDIJRCPY7/graph.json","events_json":"https://pith.science/api/pith-number/X5JGGPK5UFJFZVMDGHDIJRCPY7/events.json","paper":"https://pith.science/paper/X5JGGPK5"},"agent_actions":{"view_html":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7","download_json":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7.json","view_paper":"https://pith.science/paper/X5JGGPK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12707&json=true","fetch_graph":"https://pith.science/api/pith-number/X5JGGPK5UFJFZVMDGHDIJRCPY7/graph.json","fetch_events":"https://pith.science/api/pith-number/X5JGGPK5UFJFZVMDGHDIJRCPY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7/action/storage_attestation","attest_author":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7/action/author_attestation","sign_citation":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7/action/citation_signature","submit_replication":"https://pith.science/pith/X5JGGPK5UFJFZVMDGHDIJRCPY7/action/replication_record"}},"created_at":"2026-07-05T03:43:30.399094+00:00","updated_at":"2026-07-05T03:43:30.399094+00:00"}