{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4INHS5MXU4CTF2NA44M3Q76XZI","short_pith_number":"pith:4INHS5MX","canonical_record":{"source":{"id":"1806.07366","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T17:50:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cae7d85b5a1ddff55631b70fa27eb07d01a0ad8011cd62c9a6516cbfeae065f8","abstract_canon_sha256":"5c43859e54c56b280e576a8f0d64ee2e5f1514f538f7c5ed10ed70eff5f47a35"},"schema_version":"1.0"},"canonical_sha256":"e21a797597a70532e9a0e719b87fd7ca2036c66123e7de14314c9cf8640ccbdf","source":{"kind":"arxiv","id":"1806.07366","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07366","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07366v5","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07366","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"4INHS5MXU4CT","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4INHS5MXU4CTF2NA","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4INHS5MX","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4INHS5MXU4CTF2NA44M3Q76XZI","target":"record","payload":{"canonical_record":{"source":{"id":"1806.07366","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T17:50:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cae7d85b5a1ddff55631b70fa27eb07d01a0ad8011cd62c9a6516cbfeae065f8","abstract_canon_sha256":"5c43859e54c56b280e576a8f0d64ee2e5f1514f538f7c5ed10ed70eff5f47a35"},"schema_version":"1.0"},"canonical_sha256":"e21a797597a70532e9a0e719b87fd7ca2036c66123e7de14314c9cf8640ccbdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.504629Z","signature_b64":"gMZ+ikrt+GY2hpe5ha0Od/t7R/2kQk1HcY9yoWaVYPN0S3mo/7XgJXabdYnXSs0XEBu9ffmE8IYhJ1NmlshoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e21a797597a70532e9a0e719b87fd7ca2036c66123e7de14314c9cf8640ccbdf","last_reissued_at":"2026-05-17T23:38:52.504180Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.504180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.07366","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/5AdwKO8bw4ZOjPKibeLFcmomH4rRDn4tk50iwPqNtBri0qtehAa4ItPyi4foJxAURpZ789d86d3BmCICZd0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:49:16.512481Z"},"content_sha256":"b36e006918d7cc73b0d7f96562b1039b67b0e0ba42843ca7a765fce2f2acf4b6","schema_version":"1.0","event_id":"sha256:b36e006918d7cc73b0d7f96562b1039b67b0e0ba42843ca7a765fce2f2acf4b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4INHS5MXU4CTF2NA44M3Q76XZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Ordinary Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Deep neural networks can replace discrete layers with continuous dynamics defined by ordinary differential equations.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Jesse Bettencourt, Ricky T. Q. Chen, Yulia Rubanova","submitted_at":"2018-06-19T17:50:12Z","abstract_excerpt":"We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a neural network can be trained to produce a vector field whose integral yields useful representations, and that standard ODE solvers remain numerically stable and differentiable enough for end-to-end gradient descent across the range of problems considered.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural networks are redefined as continuous dynamical systems by learning the derivative of the hidden state with a neural network and integrating it with an ODE solver.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Deep neural networks can replace discrete layers with continuous dynamics defined by ordinary differential equations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"abc96746c8234081dcaad4738c14dd9557ecf382d7526a05e789a62840b98134"},"source":{"id":"1806.07366","kind":"arxiv","version":5},"verdict":{"id":"6da4881e-7ef9-4968-839f-2b0efd2c0cfd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T12:56:04.870070Z","strongest_claim":"We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver.","one_line_summary":"Neural networks are redefined as continuous dynamical systems by learning the derivative of the hidden state with a neural network and integrating it with an ODE solver.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a neural network can be trained to produce a vector field whose integral yields useful representations, and that standard ODE solvers remain numerically stable and differentiable enough for end-to-end gradient descent across the range of problems considered.","pith_extraction_headline":"Deep neural networks can replace discrete layers with continuous dynamics defined by ordinary differential equations."},"references":{"count":60,"sample":[{"doi":"","year":2011,"title":"Computationally efficient convolved multiple output G aussian processes","work_id":"a79ccadd-e746-419c-8444-fcba767fd3b6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"OptNet : Differentiable optimization as a layer in neural networks","work_id":"3b7f8d99-7b4a-4bdb-9e76-305ba58e9a5b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"A general-purpose software framework for dynamic optimization","work_id":"f244a44e-8889-43b2-be19-547832ef321b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"CasADi -- A software framework for nonlinear optimization and optimal control","work_id":"c5e1095a-3dfa-41f5-a35c-16af5c5a3219","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Automatic differentiation in machine learning: a survey","work_id":"8abd3335-a598-4a1c-82f1-435c37825259","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"81e54cc4e9d8e00e01936c37c564cb69b86b298f26e3b1411a1aa0b3d412b5df","internal_anchors":16},"formal_canon":{"evidence_count":3,"snapshot_sha256":"4941d4f57c642bb9ff2b1966790074421c88e13c5b66503d45885f99b68d26c8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"6da4881e-7ef9-4968-839f-2b0efd2c0cfd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duZgBjQSqhO+tC8nMWONaLG1k3hcRXjLAAdU/wBWOmbFkwf2squANIx0sVbj+X9hSwgTyZM6O49YBVsx5hczBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:49:16.513592Z"},"content_sha256":"3116a94fa0b1274bc5ce68b40b1c00717d7698ef2469177a7b6ea4786db3cc61","schema_version":"1.0","event_id":"sha256:3116a94fa0b1274bc5ce68b40b1c00717d7698ef2469177a7b6ea4786db3cc61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4INHS5MXU4CTF2NA44M3Q76XZI/bundle.json","state_url":"https://pith.science/pith/4INHS5MXU4CTF2NA44M3Q76XZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4INHS5MXU4CTF2NA44M3Q76XZI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T22:49:16Z","links":{"resolver":"https://pith.science/pith/4INHS5MXU4CTF2NA44M3Q76XZI","bundle":"https://pith.science/pith/4INHS5MXU4CTF2NA44M3Q76XZI/bundle.json","state":"https://pith.science/pith/4INHS5MXU4CTF2NA44M3Q76XZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4INHS5MXU4CTF2NA44M3Q76XZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4INHS5MXU4CTF2NA44M3Q76XZI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5c43859e54c56b280e576a8f0d64ee2e5f1514f538f7c5ed10ed70eff5f47a35","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T17:50:12Z","title_canon_sha256":"cae7d85b5a1ddff55631b70fa27eb07d01a0ad8011cd62c9a6516cbfeae065f8"},"schema_version":"1.0","source":{"id":"1806.07366","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07366","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07366v5","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07366","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"4INHS5MXU4CT","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4INHS5MXU4CTF2NA","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4INHS5MX","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:3116a94fa0b1274bc5ce68b40b1c00717d7698ef2469177a7b6ea4786db3cc61","target":"graph","created_at":"2026-05-17T23:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a neural network can be trained to produce a vector field whose integral yields useful representations, and that standard ODE solvers remain numerically stable and differentiable enough for end-to-end gradient descent across the range of problems considered."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Neural networks are redefined as continuous dynamical systems by learning the derivative of the hidden state with a neural network and integrating it with an ODE solver."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Deep neural networks can replace discrete layers with continuous dynamics defined by ordinary differential equations."}],"snapshot_sha256":"abc96746c8234081dcaad4738c14dd9557ecf382d7526a05e789a62840b98134"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"4941d4f57c642bb9ff2b1966790074421c88e13c5b66503d45885f99b68d26c8"},"paper":{"abstract_excerpt":"We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, ","authors_text":"David Duvenaud, Jesse Bettencourt, Ricky T. Q. Chen, Yulia Rubanova","cross_cats":["cs.AI","stat.ML"],"headline":"Deep neural networks can replace discrete layers with continuous dynamics defined by ordinary differential equations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T17:50:12Z","title":"Neural Ordinary Differential Equations"},"references":{"count":60,"internal_anchors":16,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Computationally efficient convolved multiple output G aussian processes","work_id":"a79ccadd-e746-419c-8444-fcba767fd3b6","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"OptNet : Differentiable optimization as a layer in neural networks","work_id":"3b7f8d99-7b4a-4bdb-9e76-305ba58e9a5b","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A general-purpose software framework for dynamic optimization","work_id":"f244a44e-8889-43b2-be19-547832ef321b","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"CasADi -- A software framework for nonlinear optimization and optimal control","work_id":"c5e1095a-3dfa-41f5-a35c-16af5c5a3219","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Automatic differentiation in machine learning: a survey","work_id":"8abd3335-a598-4a1c-82f1-435c37825259","year":2018}],"snapshot_sha256":"81e54cc4e9d8e00e01936c37c564cb69b86b298f26e3b1411a1aa0b3d412b5df"},"source":{"id":"1806.07366","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-15T12:56:04.870070Z","id":"6da4881e-7ef9-4968-839f-2b0efd2c0cfd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Neural networks are redefined as continuous dynamical systems by learning the derivative of the hidden state with a neural network and integrating it with an ODE solver.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Deep neural networks can replace discrete layers with continuous dynamics defined by ordinary differential equations.","strongest_claim":"We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver.","weakest_assumption":"That a neural network can be trained to produce a vector field whose integral yields useful representations, and that standard ODE solvers remain numerically stable and differentiable enough for end-to-end gradient descent across the range of problems considered."}},"verdict_id":"6da4881e-7ef9-4968-839f-2b0efd2c0cfd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b36e006918d7cc73b0d7f96562b1039b67b0e0ba42843ca7a765fce2f2acf4b6","target":"record","created_at":"2026-05-17T23:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5c43859e54c56b280e576a8f0d64ee2e5f1514f538f7c5ed10ed70eff5f47a35","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T17:50:12Z","title_canon_sha256":"cae7d85b5a1ddff55631b70fa27eb07d01a0ad8011cd62c9a6516cbfeae065f8"},"schema_version":"1.0","source":{"id":"1806.07366","kind":"arxiv","version":5}},"canonical_sha256":"e21a797597a70532e9a0e719b87fd7ca2036c66123e7de14314c9cf8640ccbdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e21a797597a70532e9a0e719b87fd7ca2036c66123e7de14314c9cf8640ccbdf","first_computed_at":"2026-05-17T23:38:52.504180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.504180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gMZ+ikrt+GY2hpe5ha0Od/t7R/2kQk1HcY9yoWaVYPN0S3mo/7XgJXabdYnXSs0XEBu9ffmE8IYhJ1NmlshoCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.504629Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.07366","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b36e006918d7cc73b0d7f96562b1039b67b0e0ba42843ca7a765fce2f2acf4b6","sha256:3116a94fa0b1274bc5ce68b40b1c00717d7698ef2469177a7b6ea4786db3cc61"],"state_sha256":"84251bc585a4192e8d9b7901c7e2c6d721139da2ffe1c9aface66c8df5de8b31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yuxhcm7LxNQBcZIRDFANyOzxuYB1CC3ee5nqNlZ28gug+Ynw49cuIK2Pwl1zBwDTY/TNFOPo3wUoTtsuvQkUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:49:16.518543Z","bundle_sha256":"46c36ebac1895c0a6f8fb1a634f99713d142dac8f63bea2ee4e83f7e049d521a"}}