{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YX7LESGOMJSDBYHL5EB5CAESNJ","short_pith_number":"pith:YX7LESGO","schema_version":"1.0","canonical_sha256":"c5feb248ce626430e0ebe903d100926a567680729f313874c119eab810039bfa","source":{"kind":"arxiv","id":"2607.10858","version":1},"attestation_state":"computed","paper":{"title":"Structure-Preserving Neural ODEs via Nonstandard Finite Difference Discretization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","physics.comp-ph"],"primary_cat":"math.NA","authors_text":"Achraf Zinihi, Matthias Ehrhardt, Moulay Rchid Sidi Ammi","submitted_at":"2026-07-12T17:45:05Z","abstract_excerpt":"Although neural ordinary differential equations (NODEs) are a powerful framework for learning continuous-time dynamics, they generally do not preserve essential qualitative properties, such as positivity. We propose a structure-preserving Neural ODE framework based on nonstandard finite difference (NSFD) discretization. The learned dynamics are parameterized by nonnegative production and destruction rates, yielding an explicit, differentiable update that integrates seamlessly into standard automatic differentiation pipelines. We prove that the resulting scheme unconditionally preserves positiv"},"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":"2607.10858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-07-12T17:45:05Z","cross_cats_sorted":["cs.NA","physics.comp-ph"],"title_canon_sha256":"45d2012f0f877c23a75ea72cc95b73bd48ff68fec001dca4fb755a1be726ed33","abstract_canon_sha256":"f5ae81266819c2fac392b9ef3649e9d5707d5ebbfcc12dcab2856fc6bef46ecf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:43.943208Z","signature_b64":"d75baQ/SWPnO2qQS5sqJQI2dn4/10vvUOHiXuDGbEdaadaYvv9KMb1HGsLbnDxcTsF2toitsUiJFkZKk5GUSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5feb248ce626430e0ebe903d100926a567680729f313874c119eab810039bfa","last_reissued_at":"2026-07-14T01:21:43.942370Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:43.942370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Preserving Neural ODEs via Nonstandard Finite Difference Discretization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","physics.comp-ph"],"primary_cat":"math.NA","authors_text":"Achraf Zinihi, Matthias Ehrhardt, Moulay Rchid Sidi Ammi","submitted_at":"2026-07-12T17:45:05Z","abstract_excerpt":"Although neural ordinary differential equations (NODEs) are a powerful framework for learning continuous-time dynamics, they generally do not preserve essential qualitative properties, such as positivity. We propose a structure-preserving Neural ODE framework based on nonstandard finite difference (NSFD) discretization. The learned dynamics are parameterized by nonnegative production and destruction rates, yielding an explicit, differentiable update that integrates seamlessly into standard automatic differentiation pipelines. We prove that the resulting scheme unconditionally preserves positiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10858","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/2607.10858/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":"2607.10858","created_at":"2026-07-14T01:21:43.942807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10858v1","created_at":"2026-07-14T01:21:43.942807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10858","created_at":"2026-07-14T01:21:43.942807+00:00"},{"alias_kind":"pith_short_12","alias_value":"YX7LESGOMJSD","created_at":"2026-07-14T01:21:43.942807+00:00"},{"alias_kind":"pith_short_16","alias_value":"YX7LESGOMJSDBYHL","created_at":"2026-07-14T01:21:43.942807+00:00"},{"alias_kind":"pith_short_8","alias_value":"YX7LESGO","created_at":"2026-07-14T01:21:43.942807+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/YX7LESGOMJSDBYHL5EB5CAESNJ","json":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ.json","graph_json":"https://pith.science/api/pith-number/YX7LESGOMJSDBYHL5EB5CAESNJ/graph.json","events_json":"https://pith.science/api/pith-number/YX7LESGOMJSDBYHL5EB5CAESNJ/events.json","paper":"https://pith.science/paper/YX7LESGO"},"agent_actions":{"view_html":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ","download_json":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ.json","view_paper":"https://pith.science/paper/YX7LESGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10858&json=true","fetch_graph":"https://pith.science/api/pith-number/YX7LESGOMJSDBYHL5EB5CAESNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YX7LESGOMJSDBYHL5EB5CAESNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ/action/storage_attestation","attest_author":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ/action/author_attestation","sign_citation":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ/action/citation_signature","submit_replication":"https://pith.science/pith/YX7LESGOMJSDBYHL5EB5CAESNJ/action/replication_record"}},"created_at":"2026-07-14T01:21:43.942807+00:00","updated_at":"2026-07-14T01:21:43.942807+00:00"}