{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BNDFJHUIYFS6ANOE3ZGDZGQFFP","short_pith_number":"pith:BNDFJHUI","schema_version":"1.0","canonical_sha256":"0b46549e88c165e035c4de4c3c9a052bfb1843449f594746e1bd9f876977b245","source":{"kind":"arxiv","id":"2312.05946","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty Propagation through Trained Deep Neural Networks Using Factor Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhinav Rajvanshi, Angel Daruna, Han-Pang Chiu, Yi Yao, Yunye Gong","submitted_at":"2023-12-10T17:26:27Z","abstract_excerpt":"Predictive uncertainty estimation remains a challenging problem precluding the use of deep neural networks as subsystems within safety-critical applications. Aleatoric uncertainty is a component of predictive uncertainty that cannot be reduced through model improvements. Uncertainty propagation seeks to estimate aleatoric uncertainty by propagating input uncertainties to network predictions. Existing uncertainty propagation techniques use one-way information flows, propagating uncertainties layer-by-layer or across the entire neural network while relying either on sampling or analytical techni"},"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":"2312.05946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T17:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3612dfc3e0f7c5f529e41cea4bff711177b3fa0ced1189d56e87a182abebe115","abstract_canon_sha256":"ac2faa81f349f89bc93bfe5b061341c9d4f8a3268fb474e9f0bfa2c826c4cc57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:35.442744Z","signature_b64":"2374qaGLgBn5WAFfc7+r4X4qtCTJd6hK8SBVUgLGtGHN3t8CUlHEIp6Yz18S1TUxmff45LCsDO6bHPzc+7F5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b46549e88c165e035c4de4c3c9a052bfb1843449f594746e1bd9f876977b245","last_reissued_at":"2026-07-05T07:22:35.441021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:35.441021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Propagation through Trained Deep Neural Networks Using Factor Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhinav Rajvanshi, Angel Daruna, Han-Pang Chiu, Yi Yao, Yunye Gong","submitted_at":"2023-12-10T17:26:27Z","abstract_excerpt":"Predictive uncertainty estimation remains a challenging problem precluding the use of deep neural networks as subsystems within safety-critical applications. Aleatoric uncertainty is a component of predictive uncertainty that cannot be reduced through model improvements. Uncertainty propagation seeks to estimate aleatoric uncertainty by propagating input uncertainties to network predictions. Existing uncertainty propagation techniques use one-way information flows, propagating uncertainties layer-by-layer or across the entire neural network while relying either on sampling or analytical techni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05946","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/2312.05946/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":"2312.05946","created_at":"2026-07-05T07:22:35.441078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05946v1","created_at":"2026-07-05T07:22:35.441078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05946","created_at":"2026-07-05T07:22:35.441078+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNDFJHUIYFS6","created_at":"2026-07-05T07:22:35.441078+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNDFJHUIYFS6ANOE","created_at":"2026-07-05T07:22:35.441078+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNDFJHUI","created_at":"2026-07-05T07:22:35.441078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP","json":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP.json","graph_json":"https://pith.science/api/pith-number/BNDFJHUIYFS6ANOE3ZGDZGQFFP/graph.json","events_json":"https://pith.science/api/pith-number/BNDFJHUIYFS6ANOE3ZGDZGQFFP/events.json","paper":"https://pith.science/paper/BNDFJHUI"},"agent_actions":{"view_html":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP","download_json":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP.json","view_paper":"https://pith.science/paper/BNDFJHUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05946&json=true","fetch_graph":"https://pith.science/api/pith-number/BNDFJHUIYFS6ANOE3ZGDZGQFFP/graph.json","fetch_events":"https://pith.science/api/pith-number/BNDFJHUIYFS6ANOE3ZGDZGQFFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP/action/storage_attestation","attest_author":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP/action/author_attestation","sign_citation":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP/action/citation_signature","submit_replication":"https://pith.science/pith/BNDFJHUIYFS6ANOE3ZGDZGQFFP/action/replication_record"}},"created_at":"2026-07-05T07:22:35.441078+00:00","updated_at":"2026-07-05T07:22:35.441078+00:00"}