{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DTFMAZ65RO4K25W3BXFN2J7WRO","short_pith_number":"pith:DTFMAZ65","schema_version":"1.0","canonical_sha256":"1ccac067dd8bb8ad76db0dcadd27f68ba1442ad1c729d724a0bbd131632587c9","source":{"kind":"arxiv","id":"1907.08982","version":2},"attestation_state":"computed","paper":{"title":"Noise Regularization for Conditional Density Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Fabio Ferreira, Jonas Rothfuss, Maxim Ulrich, Simon Boehm, Simon Walther, Tamim Asfour","submitted_at":"2019-07-21T14:17:28Z","abstract_excerpt":"Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability density from data. Though highly expressive, neural network based CDE models can suffer from severe over-fitting when trained with the maximum likelihood objective. Due to the inherent structure of such models, classical regularization approaches in the parameter space are rendered ineffective. To address this issue, we develop a model-agnostic noise regularization method for CDE that adds random perturbations to the da"},"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":"1907.08982","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-07-21T14:17:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ab3b46b3e6df4f0c9d8faab80c7209c851d62882ac20ea1b8e2f94f33e0efba","abstract_canon_sha256":"1cdfaf087f2959bed3a7534f7ad7f8237faf79434362d604f23658d8c85cd055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:43.653612Z","signature_b64":"Q60OgOUFA5/btcKgze+VLdfuMBJ9QBtRxm16jfbXfqCZTeNnMYEqDFWTY92lNssMONeswJ5sMijaIPG+pNNGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ccac067dd8bb8ad76db0dcadd27f68ba1442ad1c729d724a0bbd131632587c9","last_reissued_at":"2026-07-05T00:40:43.653141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:43.653141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise Regularization for Conditional Density Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Fabio Ferreira, Jonas Rothfuss, Maxim Ulrich, Simon Boehm, Simon Walther, Tamim Asfour","submitted_at":"2019-07-21T14:17:28Z","abstract_excerpt":"Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability density from data. Though highly expressive, neural network based CDE models can suffer from severe over-fitting when trained with the maximum likelihood objective. Due to the inherent structure of such models, classical regularization approaches in the parameter space are rendered ineffective. To address this issue, we develop a model-agnostic noise regularization method for CDE that adds random perturbations to the da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08982","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/1907.08982/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":"1907.08982","created_at":"2026-07-05T00:40:43.653209+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08982v2","created_at":"2026-07-05T00:40:43.653209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08982","created_at":"2026-07-05T00:40:43.653209+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTFMAZ65RO4K","created_at":"2026-07-05T00:40:43.653209+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTFMAZ65RO4K25W3","created_at":"2026-07-05T00:40:43.653209+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTFMAZ65","created_at":"2026-07-05T00:40:43.653209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13476","citing_title":"Variational Autoencoder Framework for Hyperspectral Retrievals (Hyper-VAE) of Phytoplankton Absorption and Chlorophyll a in Coastal Waters for NASA's EMIT and PACE Missions","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO","json":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO.json","graph_json":"https://pith.science/api/pith-number/DTFMAZ65RO4K25W3BXFN2J7WRO/graph.json","events_json":"https://pith.science/api/pith-number/DTFMAZ65RO4K25W3BXFN2J7WRO/events.json","paper":"https://pith.science/paper/DTFMAZ65"},"agent_actions":{"view_html":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO","download_json":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO.json","view_paper":"https://pith.science/paper/DTFMAZ65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08982&json=true","fetch_graph":"https://pith.science/api/pith-number/DTFMAZ65RO4K25W3BXFN2J7WRO/graph.json","fetch_events":"https://pith.science/api/pith-number/DTFMAZ65RO4K25W3BXFN2J7WRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO/action/storage_attestation","attest_author":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO/action/author_attestation","sign_citation":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO/action/citation_signature","submit_replication":"https://pith.science/pith/DTFMAZ65RO4K25W3BXFN2J7WRO/action/replication_record"}},"created_at":"2026-07-05T00:40:43.653209+00:00","updated_at":"2026-07-05T00:40:43.653209+00:00"}