{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IEGEXXNPRXLWVF4HYCROVM43QX","short_pith_number":"pith:IEGEXXNP","schema_version":"1.0","canonical_sha256":"410c4bddaf8dd76a9787c0a2eab39b85dd41f6409eaccd0d0c077feff5bccc10","source":{"kind":"arxiv","id":"2008.02389","version":1},"attestation_state":"computed","paper":{"title":"Continuous-in-Depth Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro F. Queiruga, Dane Taylor, Michael W. Mahoney, N. Benjamin Erichson","submitted_at":"2020-08-05T22:54:09Z","abstract_excerpt":"Recent work has attempted to interpret residual networks (ResNets) as one step of a forward Euler discretization of an ordinary differential equation, focusing mainly on syntactic algebraic similarities between the two systems. Discrete dynamical integrators of continuous dynamical systems, however, have a much richer structure. We first show that ResNets fail to be meaningful dynamical integrators in this richer sense. We then demonstrate that neural network models can learn to represent continuous dynamical systems, with this richer structure and properties, by embedding them into higher-ord"},"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":"2008.02389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-05T22:54:09Z","cross_cats_sorted":["math.DS","stat.ML"],"title_canon_sha256":"278459ae3410ec30e92a9568350f7dd5eba7d26572cc656d0b1ad2fcdb48d135","abstract_canon_sha256":"abc9779cd7c20d2cee831a882ac05783b3a6525d0bc86c2e098912aafe32c474"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:04.615979Z","signature_b64":"py20fi/cxLDtuVVhY635V1ZBUw84QNgMjHKSXVrqNHwNDlJRcr8/vqZdyavGCnG0tfdF5xm+J8SkZh/9oVVXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"410c4bddaf8dd76a9787c0a2eab39b85dd41f6409eaccd0d0c077feff5bccc10","last_reissued_at":"2026-07-05T01:25:04.615478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:04.615478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous-in-Depth Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro F. Queiruga, Dane Taylor, Michael W. Mahoney, N. Benjamin Erichson","submitted_at":"2020-08-05T22:54:09Z","abstract_excerpt":"Recent work has attempted to interpret residual networks (ResNets) as one step of a forward Euler discretization of an ordinary differential equation, focusing mainly on syntactic algebraic similarities between the two systems. Discrete dynamical integrators of continuous dynamical systems, however, have a much richer structure. We first show that ResNets fail to be meaningful dynamical integrators in this richer sense. We then demonstrate that neural network models can learn to represent continuous dynamical systems, with this richer structure and properties, by embedding them into higher-ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02389","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/2008.02389/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":"2008.02389","created_at":"2026-07-05T01:25:04.615534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02389v1","created_at":"2026-07-05T01:25:04.615534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02389","created_at":"2026-07-05T01:25:04.615534+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEGEXXNPRXLW","created_at":"2026-07-05T01:25:04.615534+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEGEXXNPRXLWVF4H","created_at":"2026-07-05T01:25:04.615534+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEGEXXNP","created_at":"2026-07-05T01:25:04.615534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2010.02502","citing_title":"Denoising Diffusion Implicit Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22104","citing_title":"TRASE-NODEs: Trajectory Sensitivity-aware Neural Ordinary Differential Equations for Efficient Dynamic Modeling","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08539","citing_title":"Continuity Laws for Sequential Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX","json":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX.json","graph_json":"https://pith.science/api/pith-number/IEGEXXNPRXLWVF4HYCROVM43QX/graph.json","events_json":"https://pith.science/api/pith-number/IEGEXXNPRXLWVF4HYCROVM43QX/events.json","paper":"https://pith.science/paper/IEGEXXNP"},"agent_actions":{"view_html":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX","download_json":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX.json","view_paper":"https://pith.science/paper/IEGEXXNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02389&json=true","fetch_graph":"https://pith.science/api/pith-number/IEGEXXNPRXLWVF4HYCROVM43QX/graph.json","fetch_events":"https://pith.science/api/pith-number/IEGEXXNPRXLWVF4HYCROVM43QX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX/action/storage_attestation","attest_author":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX/action/author_attestation","sign_citation":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX/action/citation_signature","submit_replication":"https://pith.science/pith/IEGEXXNPRXLWVF4HYCROVM43QX/action/replication_record"}},"created_at":"2026-07-05T01:25:04.615534+00:00","updated_at":"2026-07-05T01:25:04.615534+00:00"}