{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KLFQNE2B7M2XIH7TQWO6H4FMTZ","short_pith_number":"pith:KLFQNE2B","schema_version":"1.0","canonical_sha256":"52cb069341fb35741ff3859de3f0ac9e48e9dff95859997449ade950c1f85f5e","source":{"kind":"arxiv","id":"1805.03430","version":1},"attestation_state":"computed","paper":{"title":"Deep Directional Statistics: Pose Estimation with Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peter Gehler, Sebastian Nowozin, Sergey Prokudin","submitted_at":"2018-05-09T09:22:09Z","abstract_excerpt":"Modern deep learning systems successfully solve many perception tasks such as object pose estimation when the input image is of high quality. However, in challenging imaging conditions such as on low-resolution images or when the image is corrupted by imaging artifacts, current systems degrade considerably in accuracy. While a loss in performance is unavoidable, we would like our models to quantify their uncertainty in order to achieve robustness against images of varying quality. Probabilistic deep learning models combine the expressive power of deep learning with uncertainty quantification. "},"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":"1805.03430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T09:22:09Z","cross_cats_sorted":[],"title_canon_sha256":"f1483cab0b1a05986ff26512cdb6573ad6a6f4a91355a096cc543acd1998ab11","abstract_canon_sha256":"f66b0608a5ea08c553971a4d86d1102420ba21c17ddabcc7ab3185657a7b0ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:20.245705Z","signature_b64":"Qqp5Cb9MaBZfKzbXoN6uoA2Ywgg8CcbyUtVYrc3E0gNbpH62u+Byg9VccmRoPQpnXeHkLXdu4j0C/q2xxajEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52cb069341fb35741ff3859de3f0ac9e48e9dff95859997449ade950c1f85f5e","last_reissued_at":"2026-05-18T00:16:20.245176Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:20.245176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Directional Statistics: Pose Estimation with Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peter Gehler, Sebastian Nowozin, Sergey Prokudin","submitted_at":"2018-05-09T09:22:09Z","abstract_excerpt":"Modern deep learning systems successfully solve many perception tasks such as object pose estimation when the input image is of high quality. However, in challenging imaging conditions such as on low-resolution images or when the image is corrupted by imaging artifacts, current systems degrade considerably in accuracy. While a loss in performance is unavoidable, we would like our models to quantify their uncertainty in order to achieve robustness against images of varying quality. Probabilistic deep learning models combine the expressive power of deep learning with uncertainty quantification. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03430","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":""},"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":"1805.03430","created_at":"2026-05-18T00:16:20.245263+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.03430v1","created_at":"2026-05-18T00:16:20.245263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03430","created_at":"2026-05-18T00:16:20.245263+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLFQNE2B7M2X","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLFQNE2B7M2XIH7T","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLFQNE2B","created_at":"2026-05-18T12:32:33.847187+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/KLFQNE2B7M2XIH7TQWO6H4FMTZ","json":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ.json","graph_json":"https://pith.science/api/pith-number/KLFQNE2B7M2XIH7TQWO6H4FMTZ/graph.json","events_json":"https://pith.science/api/pith-number/KLFQNE2B7M2XIH7TQWO6H4FMTZ/events.json","paper":"https://pith.science/paper/KLFQNE2B"},"agent_actions":{"view_html":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ","download_json":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ.json","view_paper":"https://pith.science/paper/KLFQNE2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.03430&json=true","fetch_graph":"https://pith.science/api/pith-number/KLFQNE2B7M2XIH7TQWO6H4FMTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KLFQNE2B7M2XIH7TQWO6H4FMTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ/action/storage_attestation","attest_author":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ/action/author_attestation","sign_citation":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ/action/citation_signature","submit_replication":"https://pith.science/pith/KLFQNE2B7M2XIH7TQWO6H4FMTZ/action/replication_record"}},"created_at":"2026-05-18T00:16:20.245263+00:00","updated_at":"2026-05-18T00:16:20.245263+00:00"}