{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BZ7FGCIA3Q7LJ77JR2OCCSSWVT","short_pith_number":"pith:BZ7FGCIA","schema_version":"1.0","canonical_sha256":"0e7e530900dc3eb4ffe98e9c214a56acfedc2df6a09e5908cc782a69ead44633","source":{"kind":"arxiv","id":"1904.12933","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Neural Networks in the Eye of Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Isaac Chuang, Lior Horesh, Murphy Yuezhen Niu","submitted_at":"2019-04-29T20:16:20Z","abstract_excerpt":"To understand the fundamental trade-offs between training stability, temporal dynamics and architectural complexity of recurrent neural networks~(RNNs), we directly analyze RNN architectures using numerical methods of ordinary differential equations~(ODEs). We define a general family of RNNs--the ODERNNs--by relating the composition rules of RNNs to integration methods of ODEs at discrete time steps. We show that the degree of RNN's functional nonlinearity $n$ and the range of its temporal memory $t$ can be mapped to the corresponding stage of Runge-Kutta recursion and the order of time-deriva"},"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":"1904.12933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T20:16:20Z","cross_cats_sorted":["quant-ph","stat.ML"],"title_canon_sha256":"4c48d54551514bf713a4ed214235675153a0a96bb6bf151b1f12436c4aa45012","abstract_canon_sha256":"58f6c69c8fadd70e3479f1d6a7b718ea033fee921cb231a3ba734370f359fecb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:24.432585Z","signature_b64":"cv1tcUuQhfGuUrUe6acx8g+wOKK1HxYV9ZRj/u8euUYdztvETExD3k8CSPadsLRwvf3viirgR7CDn5Kxki8FAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e7e530900dc3eb4ffe98e9c214a56acfedc2df6a09e5908cc782a69ead44633","last_reissued_at":"2026-05-17T23:47:24.432081Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:24.432081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Neural Networks in the Eye of Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Isaac Chuang, Lior Horesh, Murphy Yuezhen Niu","submitted_at":"2019-04-29T20:16:20Z","abstract_excerpt":"To understand the fundamental trade-offs between training stability, temporal dynamics and architectural complexity of recurrent neural networks~(RNNs), we directly analyze RNN architectures using numerical methods of ordinary differential equations~(ODEs). We define a general family of RNNs--the ODERNNs--by relating the composition rules of RNNs to integration methods of ODEs at discrete time steps. We show that the degree of RNN's functional nonlinearity $n$ and the range of its temporal memory $t$ can be mapped to the corresponding stage of Runge-Kutta recursion and the order of time-deriva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12933","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":""},"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":"1904.12933","created_at":"2026-05-17T23:47:24.432157+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12933v1","created_at":"2026-05-17T23:47:24.432157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12933","created_at":"2026-05-17T23:47:24.432157+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZ7FGCIA3Q7L","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZ7FGCIA3Q7LJ77J","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZ7FGCIA","created_at":"2026-05-18T12:33:12.712433+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/BZ7FGCIA3Q7LJ77JR2OCCSSWVT","json":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT.json","graph_json":"https://pith.science/api/pith-number/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/graph.json","events_json":"https://pith.science/api/pith-number/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/events.json","paper":"https://pith.science/paper/BZ7FGCIA"},"agent_actions":{"view_html":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT","download_json":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT.json","view_paper":"https://pith.science/paper/BZ7FGCIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12933&json=true","fetch_graph":"https://pith.science/api/pith-number/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/graph.json","fetch_events":"https://pith.science/api/pith-number/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/action/storage_attestation","attest_author":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/action/author_attestation","sign_citation":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/action/citation_signature","submit_replication":"https://pith.science/pith/BZ7FGCIA3Q7LJ77JR2OCCSSWVT/action/replication_record"}},"created_at":"2026-05-17T23:47:24.432157+00:00","updated_at":"2026-05-17T23:47:24.432157+00:00"}