{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SK3WFDXGS5IAMYCHCBMPDI56OI","short_pith_number":"pith:SK3WFDXG","schema_version":"1.0","canonical_sha256":"92b7628ee697500660471058f1a3be720f1fa6a286b0242afc9576ebb526e9a0","source":{"kind":"arxiv","id":"1906.01620","version":3},"attestation_state":"computed","paper":{"title":"Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fredrik K. Gustafsson, Martin Danelljan, Thomas B. Sch\\\"on","submitted_at":"2019-06-04T17:54:20Z","abstract_excerpt":"While deep neural networks have become the go-to approach in computer vision, the vast majority of these models fail to properly capture the uncertainty inherent in their predictions. Estimating this predictive uncertainty can be crucial, for example in automotive applications. In Bayesian deep learning, predictive uncertainty is commonly decomposed into the distinct types of aleatoric and epistemic uncertainty. The former can be estimated by letting a neural network output the parameters of a certain probability distribution. Epistemic uncertainty estimation is a more challenging problem, and"},"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":"1906.01620","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T17:54:20Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"af6319255a8bd218042221ed888255de829a13b376900fbf84a71f93cced212c","abstract_canon_sha256":"7c67e08b295f2b568c3604251940d416352e8e74b299049182170dd12833b1a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:06.358928Z","signature_b64":"6zOWxX3fmmNojbYNQMeDtxKq727CZ5jpW8eWTNmycHNN6Qik8HezBsECh5LjwJfjJKizIxWDVI3JGWKGjzkbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92b7628ee697500660471058f1a3be720f1fa6a286b0242afc9576ebb526e9a0","last_reissued_at":"2026-07-05T00:53:06.358430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:06.358430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fredrik K. Gustafsson, Martin Danelljan, Thomas B. Sch\\\"on","submitted_at":"2019-06-04T17:54:20Z","abstract_excerpt":"While deep neural networks have become the go-to approach in computer vision, the vast majority of these models fail to properly capture the uncertainty inherent in their predictions. Estimating this predictive uncertainty can be crucial, for example in automotive applications. In Bayesian deep learning, predictive uncertainty is commonly decomposed into the distinct types of aleatoric and epistemic uncertainty. The former can be estimated by letting a neural network output the parameters of a certain probability distribution. Epistemic uncertainty estimation is a more challenging problem, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01620","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/1906.01620/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":"1906.01620","created_at":"2026-07-05T00:53:06.358489+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01620v3","created_at":"2026-07-05T00:53:06.358489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01620","created_at":"2026-07-05T00:53:06.358489+00:00"},{"alias_kind":"pith_short_12","alias_value":"SK3WFDXGS5IA","created_at":"2026-07-05T00:53:06.358489+00:00"},{"alias_kind":"pith_short_16","alias_value":"SK3WFDXGS5IAMYCH","created_at":"2026-07-05T00:53:06.358489+00:00"},{"alias_kind":"pith_short_8","alias_value":"SK3WFDXG","created_at":"2026-07-05T00:53:06.358489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10136","citing_title":"iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI","json":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI.json","graph_json":"https://pith.science/api/pith-number/SK3WFDXGS5IAMYCHCBMPDI56OI/graph.json","events_json":"https://pith.science/api/pith-number/SK3WFDXGS5IAMYCHCBMPDI56OI/events.json","paper":"https://pith.science/paper/SK3WFDXG"},"agent_actions":{"view_html":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI","download_json":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI.json","view_paper":"https://pith.science/paper/SK3WFDXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01620&json=true","fetch_graph":"https://pith.science/api/pith-number/SK3WFDXGS5IAMYCHCBMPDI56OI/graph.json","fetch_events":"https://pith.science/api/pith-number/SK3WFDXGS5IAMYCHCBMPDI56OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI/action/storage_attestation","attest_author":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI/action/author_attestation","sign_citation":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI/action/citation_signature","submit_replication":"https://pith.science/pith/SK3WFDXGS5IAMYCHCBMPDI56OI/action/replication_record"}},"created_at":"2026-07-05T00:53:06.358489+00:00","updated_at":"2026-07-05T00:53:06.358489+00:00"}