{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GZ26LJB2NVJFQF3DESPHJ42MAC","short_pith_number":"pith:GZ26LJB2","schema_version":"1.0","canonical_sha256":"3675e5a43a6d52581763249e74f34c009d3fad9efc14081b6af07d5a10f4ba27","source":{"kind":"arxiv","id":"1912.00042","version":2},"attestation_state":"computed","paper":{"title":"Learning Likelihoods with Conditional Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christina Winkler, Daniel Worrall, Emiel Hoogeboom, Max Welling","submitted_at":"2019-11-29T19:17:58Z","abstract_excerpt":"Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high multimodality by transforming a simple base density p(z) through an invertible neural network under the change of variables formula. Such behavior is desirable in multivariate structured prediction tasks, where handcrafted per-pixel loss-based methods inadequately capture strong correlations between output dimensions. We present a study of conditional normalizing flows (CNFs), a class of NFs where the base density to output space mapping is conditioned on an input x, to "},"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":"1912.00042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-29T19:17:58Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e9d48a6853122c2648b5d309471f06c0a06718b40afd0ffc401b2cbcff0d39b7","abstract_canon_sha256":"d17a0456f1b33c9416caab18022af9046258f7bd7f7847e3803aee6021801e94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:49.134811Z","signature_b64":"SAokJYOvolCOOO6v1kCngdJ0mKJ+zq1sWWw7gEFKOk6DTpFS7EPmz86tBgkQvJg03D2OCJNzw3kNVouBkSaWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3675e5a43a6d52581763249e74f34c009d3fad9efc14081b6af07d5a10f4ba27","last_reissued_at":"2026-07-05T07:11:49.134282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:49.134282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Likelihoods with Conditional Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christina Winkler, Daniel Worrall, Emiel Hoogeboom, Max Welling","submitted_at":"2019-11-29T19:17:58Z","abstract_excerpt":"Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high multimodality by transforming a simple base density p(z) through an invertible neural network under the change of variables formula. Such behavior is desirable in multivariate structured prediction tasks, where handcrafted per-pixel loss-based methods inadequately capture strong correlations between output dimensions. We present a study of conditional normalizing flows (CNFs), a class of NFs where the base density to output space mapping is conditioned on an input x, to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00042","kind":"arxiv","version":2},"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/1912.00042/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":"1912.00042","created_at":"2026-07-05T07:11:49.134343+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00042v2","created_at":"2026-07-05T07:11:49.134343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00042","created_at":"2026-07-05T07:11:49.134343+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZ26LJB2NVJF","created_at":"2026-07-05T07:11:49.134343+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZ26LJB2NVJFQF3D","created_at":"2026-07-05T07:11:49.134343+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZ26LJB2","created_at":"2026-07-05T07:11:49.134343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08360","citing_title":"Generative Frontier Planning for Adaptive Peer-Referral Recruitment under Covariate-Dependent Arrivals","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02936","citing_title":"Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09857","citing_title":"Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31489","citing_title":"Context-Conditioned Generative Models Enable Subnational Refinement of Sparse Humanitarian Surveys","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00563","citing_title":"A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22489","citing_title":"Machine Learning Techniques for Astrophysics and Cosmology: Lyman-$\\alpha$ forest","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04153","citing_title":"Data-Driven Predictions for Dark Photon and Millicharged Particle Production","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09374","citing_title":"Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14399","citing_title":"Factored Classifier-Free Guidance","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08999","citing_title":"Non-Parametric Rehearsal Learning via Conditional Mean Embeddings","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06272","citing_title":"A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04955","citing_title":"Order-based Rehearsal Learning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC","json":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC.json","graph_json":"https://pith.science/api/pith-number/GZ26LJB2NVJFQF3DESPHJ42MAC/graph.json","events_json":"https://pith.science/api/pith-number/GZ26LJB2NVJFQF3DESPHJ42MAC/events.json","paper":"https://pith.science/paper/GZ26LJB2"},"agent_actions":{"view_html":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC","download_json":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC.json","view_paper":"https://pith.science/paper/GZ26LJB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00042&json=true","fetch_graph":"https://pith.science/api/pith-number/GZ26LJB2NVJFQF3DESPHJ42MAC/graph.json","fetch_events":"https://pith.science/api/pith-number/GZ26LJB2NVJFQF3DESPHJ42MAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC/action/storage_attestation","attest_author":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC/action/author_attestation","sign_citation":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC/action/citation_signature","submit_replication":"https://pith.science/pith/GZ26LJB2NVJFQF3DESPHJ42MAC/action/replication_record"}},"created_at":"2026-07-05T07:11:49.134343+00:00","updated_at":"2026-07-05T07:11:49.134343+00:00"}