{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3I62RCPFI44FH3WDXASRK2ED7J","short_pith_number":"pith:3I62RCPF","schema_version":"1.0","canonical_sha256":"da3da889e5473853eec3b825156883fa754a93562c740b2fefb1eef62234f27c","source":{"kind":"arxiv","id":"1810.01367","version":3},"attestation_state":"computed","paper":{"title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Ilya Sutskever, Jesse Bettencourt, Ricky T. Q. Chen, Will Grathwohl","submitted_at":"2018-10-02T16:56:37Z","abstract_excerpt":"A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants. Alternatively, the Jacobian trace can be used if the transformation is specified by an ordinary differential equation. In this paper, we use Hutchinson's trace estimator to give a scalable unbiased estimate of the log-density. The result is a continuous-time invertible generative model with unbiased density estimation an"},"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":"1810.01367","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T16:56:37Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"f5f9ca6138abf72ab9b54304baf583ab76b1c0ea71f2b10181b71514e585e909","abstract_canon_sha256":"37a5441156a7e5a3c7611353d7297161d8e0599ec387313aee64ded3ff94c252"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:44.178442Z","signature_b64":"z1sN2TKX0/RLpSbNGgSuq6ICHLvI21h1n57L6+I8YeNjK0UPKuXkFN/pVvJjxD0Zds9g91YILGAnNx6j0eiuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3da889e5473853eec3b825156883fa754a93562c740b2fefb1eef62234f27c","last_reissued_at":"2026-05-18T00:02:44.177933Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:44.177933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Ilya Sutskever, Jesse Bettencourt, Ricky T. Q. Chen, Will Grathwohl","submitted_at":"2018-10-02T16:56:37Z","abstract_excerpt":"A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants. Alternatively, the Jacobian trace can be used if the transformation is specified by an ordinary differential equation. In this paper, we use Hutchinson's trace estimator to give a scalable unbiased estimate of the log-density. The result is a continuous-time invertible generative model with unbiased density estimation an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01367","kind":"arxiv","version":3},"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":"1810.01367","created_at":"2026-05-18T00:02:44.178031+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01367v3","created_at":"2026-05-18T00:02:44.178031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01367","created_at":"2026-05-18T00:02:44.178031+00:00"},{"alias_kind":"pith_short_12","alias_value":"3I62RCPFI44F","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3I62RCPFI44FH3WD","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3I62RCPF","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1907.07587","citing_title":"A Differentiable Programming System to Bridge Machine Learning and Scientific Computing","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02502","citing_title":"Denoising Diffusion Implicit Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2304.12906","citing_title":"The Score-Difference Flow for Implicit Generative Modeling","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2408.09369","citing_title":"Flemme: A Flexible and Modular Learning Platform for Medical Images","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22340","citing_title":"From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17733","citing_title":"Divergence-Suppressing Couplings for Rectified Flow","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2509.20430","citing_title":"pop-cosmos: Star formation over 12 Gyr from generative modelling of a deep infrared-selected galaxy catalogue","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06508","citing_title":"Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16520","citing_title":"Saving Foundation Flow-Matching Priors for Inverse Problems","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08606","citing_title":"Constructive conditional normalizing flows","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22564","citing_title":"MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11387","citing_title":"Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06264","citing_title":"Flow Matching Guide and Code","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25137","citing_title":"Quantum Dynamics via Score Matching on Bohmian Trajectories","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02222","citing_title":"Generative Modeling with Orbit-Space Particle Flow Matching","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09769","citing_title":"Differentiable free energy surface: a variational approach to directly observing rare events using generative deep-learning models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09386","citing_title":"Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06955","citing_title":"Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06905","citing_title":"Conservative Flows: A New Paradigm of Generative Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04646","citing_title":"Training-Free Refinement of Flow Matching with Divergence-based Sampling","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J","json":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J.json","graph_json":"https://pith.science/api/pith-number/3I62RCPFI44FH3WDXASRK2ED7J/graph.json","events_json":"https://pith.science/api/pith-number/3I62RCPFI44FH3WDXASRK2ED7J/events.json","paper":"https://pith.science/paper/3I62RCPF"},"agent_actions":{"view_html":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J","download_json":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J.json","view_paper":"https://pith.science/paper/3I62RCPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01367&json=true","fetch_graph":"https://pith.science/api/pith-number/3I62RCPFI44FH3WDXASRK2ED7J/graph.json","fetch_events":"https://pith.science/api/pith-number/3I62RCPFI44FH3WDXASRK2ED7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J/action/storage_attestation","attest_author":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J/action/author_attestation","sign_citation":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J/action/citation_signature","submit_replication":"https://pith.science/pith/3I62RCPFI44FH3WDXASRK2ED7J/action/replication_record"}},"created_at":"2026-05-18T00:02:44.178031+00:00","updated_at":"2026-05-18T00:02:44.178031+00:00"}