{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PSJQ2GYM235A7E2OA6CNO77EAB","short_pith_number":"pith:PSJQ2GYM","schema_version":"1.0","canonical_sha256":"7c930d1b0cd6fa0f934e0784d77fe4007ab42e39800b626ecf8abf797a93f9b0","source":{"kind":"arxiv","id":"2207.10074","version":2},"attestation_state":"computed","paper":{"title":"Semantic uncertainty intervals for disentangled latent spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anastasios N. Angelopoulos, Phillip Isola, Stephen Bates, Swami Sankaranarayanan, Yaniv Romano","submitted_at":"2022-07-20T17:58:10Z","abstract_excerpt":"Meaningful uncertainty quantification in computer vision requires reasoning about semantic information -- say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow us to represent semantic information in disentangled latent spaces, but providing uncertainties on the semantic latent variables has remained challenging. In this work, we provide principled uncertainty intervals that are guaranteed to contain the true semantic factors for any underlying generative model. The method does the following: (1) it u"},"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":"2207.10074","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T17:58:10Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"3220d345885d8d7c0ee83815b0eb54d9c5a804b956fc940a0eaf0305c319c467","abstract_canon_sha256":"41b5e0f72afd4669b779b3f03b6774c4eeed659d974068d9136022185f1f2d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:26.458636Z","signature_b64":"60n2TDrzx4Wgq/gwQzcNdyrdZJfpC6JgdXEQy+F0r+5DWxKXeU+noOChyaR0i6nirmRnSHDNK4K21WHIWeZtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c930d1b0cd6fa0f934e0784d77fe4007ab42e39800b626ecf8abf797a93f9b0","last_reissued_at":"2026-07-05T05:21:26.458159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:26.458159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic uncertainty intervals for disentangled latent spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anastasios N. Angelopoulos, Phillip Isola, Stephen Bates, Swami Sankaranarayanan, Yaniv Romano","submitted_at":"2022-07-20T17:58:10Z","abstract_excerpt":"Meaningful uncertainty quantification in computer vision requires reasoning about semantic information -- say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow us to represent semantic information in disentangled latent spaces, but providing uncertainties on the semantic latent variables has remained challenging. In this work, we provide principled uncertainty intervals that are guaranteed to contain the true semantic factors for any underlying generative model. The method does the following: (1) it u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10074","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/2207.10074/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":"2207.10074","created_at":"2026-07-05T05:21:26.458214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10074v2","created_at":"2026-07-05T05:21:26.458214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10074","created_at":"2026-07-05T05:21:26.458214+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSJQ2GYM235A","created_at":"2026-07-05T05:21:26.458214+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSJQ2GYM235A7E2O","created_at":"2026-07-05T05:21:26.458214+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSJQ2GYM","created_at":"2026-07-05T05:21:26.458214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.09806","citing_title":"CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB","json":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB.json","graph_json":"https://pith.science/api/pith-number/PSJQ2GYM235A7E2OA6CNO77EAB/graph.json","events_json":"https://pith.science/api/pith-number/PSJQ2GYM235A7E2OA6CNO77EAB/events.json","paper":"https://pith.science/paper/PSJQ2GYM"},"agent_actions":{"view_html":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB","download_json":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB.json","view_paper":"https://pith.science/paper/PSJQ2GYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10074&json=true","fetch_graph":"https://pith.science/api/pith-number/PSJQ2GYM235A7E2OA6CNO77EAB/graph.json","fetch_events":"https://pith.science/api/pith-number/PSJQ2GYM235A7E2OA6CNO77EAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB/action/storage_attestation","attest_author":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB/action/author_attestation","sign_citation":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB/action/citation_signature","submit_replication":"https://pith.science/pith/PSJQ2GYM235A7E2OA6CNO77EAB/action/replication_record"}},"created_at":"2026-07-05T05:21:26.458214+00:00","updated_at":"2026-07-05T05:21:26.458214+00:00"}