{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IKGPWQDHSG43SKKMZMZSNPVLWD","short_pith_number":"pith:IKGPWQDH","schema_version":"1.0","canonical_sha256":"428cfb406791b9b9294ccb3326beabb0de1c8c438338e03a6e447ae1e37f2f52","source":{"kind":"arxiv","id":"2311.00377","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty quantification and out-of-distribution detection using surjective normalizing flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.LG","authors_text":"Fernando Perez-Cruz, Simon Dirmeier, Yanan Xin, Ye Hong","submitted_at":"2023-11-01T09:08:35Z","abstract_excerpt":"Reliable quantification of epistemic and aleatoric uncertainty is of crucial importance in applications where models are trained in one environment but applied to multiple different environments, often seen in real-world applications for example, in climate science or mobility analysis. We propose a simple approach using surjective normalizing flows to identify out-of-distribution data sets in deep neural network models that can be computed in a single forward pass. The method builds on recent developments in deep uncertainty quantification and generative modeling with normalizing flows. We ap"},"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":"2311.00377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T09:08:35Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"123705fa84ddfabc33ac38790ae1a279720ae81a302b768ca796fc1b69c2e765","abstract_canon_sha256":"d0f45ae4869de83a7cf60518f5559e8cf4ed87e44d3c400c2864c0467a445fa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:56.614341Z","signature_b64":"880DI3yyQIWyxA4zbuJvIUrMBtiWr8+/43p4dUVhRghS5Ezz0X3R7wpAp/d7mXUjTL+LBYicV3aZP9Ah4rTsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"428cfb406791b9b9294ccb3326beabb0de1c8c438338e03a6e447ae1e37f2f52","last_reissued_at":"2026-07-05T07:07:56.613806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:56.613806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty quantification and out-of-distribution detection using surjective normalizing flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.LG","authors_text":"Fernando Perez-Cruz, Simon Dirmeier, Yanan Xin, Ye Hong","submitted_at":"2023-11-01T09:08:35Z","abstract_excerpt":"Reliable quantification of epistemic and aleatoric uncertainty is of crucial importance in applications where models are trained in one environment but applied to multiple different environments, often seen in real-world applications for example, in climate science or mobility analysis. We propose a simple approach using surjective normalizing flows to identify out-of-distribution data sets in deep neural network models that can be computed in a single forward pass. The method builds on recent developments in deep uncertainty quantification and generative modeling with normalizing flows. We ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00377","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.00377/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":"2311.00377","created_at":"2026-07-05T07:07:56.613878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00377v1","created_at":"2026-07-05T07:07:56.613878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00377","created_at":"2026-07-05T07:07:56.613878+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKGPWQDHSG43","created_at":"2026-07-05T07:07:56.613878+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKGPWQDHSG43SKKM","created_at":"2026-07-05T07:07:56.613878+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKGPWQDH","created_at":"2026-07-05T07:07:56.613878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05657","citing_title":"Emulating compact binary population synthesis simulations with uncertainty quantification and model comparison using Bayesian normalizing flows","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD","json":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD.json","graph_json":"https://pith.science/api/pith-number/IKGPWQDHSG43SKKMZMZSNPVLWD/graph.json","events_json":"https://pith.science/api/pith-number/IKGPWQDHSG43SKKMZMZSNPVLWD/events.json","paper":"https://pith.science/paper/IKGPWQDH"},"agent_actions":{"view_html":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD","download_json":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD.json","view_paper":"https://pith.science/paper/IKGPWQDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00377&json=true","fetch_graph":"https://pith.science/api/pith-number/IKGPWQDHSG43SKKMZMZSNPVLWD/graph.json","fetch_events":"https://pith.science/api/pith-number/IKGPWQDHSG43SKKMZMZSNPVLWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD/action/storage_attestation","attest_author":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD/action/author_attestation","sign_citation":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD/action/citation_signature","submit_replication":"https://pith.science/pith/IKGPWQDHSG43SKKMZMZSNPVLWD/action/replication_record"}},"created_at":"2026-07-05T07:07:56.613878+00:00","updated_at":"2026-07-05T07:07:56.613878+00:00"}