{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KM3WB42EMPMGCOPL4LAKBHAWK5","short_pith_number":"pith:KM3WB42E","schema_version":"1.0","canonical_sha256":"533760f34463d86139ebe2c0a09c16576c7d19d1ca9b771abf33ffe1bcd447fa","source":{"kind":"arxiv","id":"1908.00598","version":3},"attestation_state":"computed","paper":{"title":"Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Federico Tombari, Francesco Ferroni, Huseyin Coskun, Janis Postels, Nassir Navab","submitted_at":"2019-08-01T19:53:35Z","abstract_excerpt":"We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one can trust predictions on new data. Recently promising works were proposed using noise injection combined with Monte-Carlo sampling at inference time to estimate this quantity (e.g. Monte-Carlo dropout). Our main contribution is an approximation of the epistemic uncertainty estimated by these methods that does not require sampling, thus notably r"},"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":"1908.00598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-01T19:53:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3371009dd32974940e50c7d680548caa797a75f1206e8b93894010f6810ecd93","abstract_canon_sha256":"fae61623cb80f06ab667de49829dc0d99dd46b2a780a821ccd30d600669d7dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:23.456079Z","signature_b64":"jMtmhg2MrT4NQuM4YyoeXrxksVgfjqAm68TT7U4+hvT+TOQa8JlIXBNsRCGtsDCUPTW05fwpHOuKaZhBBMd5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"533760f34463d86139ebe2c0a09c16576c7d19d1ca9b771abf33ffe1bcd447fa","last_reissued_at":"2026-07-05T00:23:23.455539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:23.455539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Federico Tombari, Francesco Ferroni, Huseyin Coskun, Janis Postels, Nassir Navab","submitted_at":"2019-08-01T19:53:35Z","abstract_excerpt":"We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one can trust predictions on new data. Recently promising works were proposed using noise injection combined with Monte-Carlo sampling at inference time to estimate this quantity (e.g. Monte-Carlo dropout). Our main contribution is an approximation of the epistemic uncertainty estimated by these methods that does not require sampling, thus notably r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.00598","kind":"arxiv","version":3},"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/1908.00598/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":"1908.00598","created_at":"2026-07-05T00:23:23.455604+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.00598v3","created_at":"2026-07-05T00:23:23.455604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.00598","created_at":"2026-07-05T00:23:23.455604+00:00"},{"alias_kind":"pith_short_12","alias_value":"KM3WB42EMPMG","created_at":"2026-07-05T00:23:23.455604+00:00"},{"alias_kind":"pith_short_16","alias_value":"KM3WB42EMPMGCOPL","created_at":"2026-07-05T00:23:23.455604+00:00"},{"alias_kind":"pith_short_8","alias_value":"KM3WB42E","created_at":"2026-07-05T00:23:23.455604+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/KM3WB42EMPMGCOPL4LAKBHAWK5","json":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5.json","graph_json":"https://pith.science/api/pith-number/KM3WB42EMPMGCOPL4LAKBHAWK5/graph.json","events_json":"https://pith.science/api/pith-number/KM3WB42EMPMGCOPL4LAKBHAWK5/events.json","paper":"https://pith.science/paper/KM3WB42E"},"agent_actions":{"view_html":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5","download_json":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5.json","view_paper":"https://pith.science/paper/KM3WB42E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.00598&json=true","fetch_graph":"https://pith.science/api/pith-number/KM3WB42EMPMGCOPL4LAKBHAWK5/graph.json","fetch_events":"https://pith.science/api/pith-number/KM3WB42EMPMGCOPL4LAKBHAWK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5/action/storage_attestation","attest_author":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5/action/author_attestation","sign_citation":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5/action/citation_signature","submit_replication":"https://pith.science/pith/KM3WB42EMPMGCOPL4LAKBHAWK5/action/replication_record"}},"created_at":"2026-07-05T00:23:23.455604+00:00","updated_at":"2026-07-05T00:23:23.455604+00:00"}