{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PSQ7FJIUVASGPFPZZVC2FFOSZ5","short_pith_number":"pith:PSQ7FJIU","schema_version":"1.0","canonical_sha256":"7ca1f2a514a8246795f9cd45a295d2cf644d3a6058fa7bc16cfb9da3cda3b6e7","source":{"kind":"arxiv","id":"2202.09664","version":1},"attestation_state":"computed","paper":{"title":"Accurate Prediction and Uncertainty Estimation using Decoupled Prediction Interval Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kinjal Patel, Steven Waslander","submitted_at":"2022-02-19T19:31:36Z","abstract_excerpt":"We propose a network architecture capable of reliably estimating uncertainty of regression based predictions without sacrificing accuracy. The current state-of-the-art uncertainty algorithms either fall short of achieving prediction accuracy comparable to the mean square error optimization or underestimate the variance of network predictions. We propose a decoupled network architecture that is capable of accomplishing both at the same time. We achieve this by breaking down the learning of prediction and prediction interval (PI) estimations into a two-stage training process. We use a custom los"},"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":"2202.09664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-19T19:31:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2cdc1d08420619672b87f1c96810f1e1772ac65d7a9b400600b382811d61ac6a","abstract_canon_sha256":"811b15d2c0fdea0240d88cd73b3e3857bfd39497a0acaae5aed54efcc1bfdc0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:24.674815Z","signature_b64":"dxVZkbDvsrIgA3GulmWWaj//B31UaGj46qfPJHcdSzC6tnGX1nkBTrlwtgjE0MSKbaFqPt2B+w/8N4XLN5aTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca1f2a514a8246795f9cd45a295d2cf644d3a6058fa7bc16cfb9da3cda3b6e7","last_reissued_at":"2026-07-05T03:58:24.674435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:24.674435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate Prediction and Uncertainty Estimation using Decoupled Prediction Interval Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kinjal Patel, Steven Waslander","submitted_at":"2022-02-19T19:31:36Z","abstract_excerpt":"We propose a network architecture capable of reliably estimating uncertainty of regression based predictions without sacrificing accuracy. The current state-of-the-art uncertainty algorithms either fall short of achieving prediction accuracy comparable to the mean square error optimization or underestimate the variance of network predictions. We propose a decoupled network architecture that is capable of accomplishing both at the same time. We achieve this by breaking down the learning of prediction and prediction interval (PI) estimations into a two-stage training process. We use a custom los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09664","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/2202.09664/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":"2202.09664","created_at":"2026-07-05T03:58:24.674496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09664v1","created_at":"2026-07-05T03:58:24.674496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09664","created_at":"2026-07-05T03:58:24.674496+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSQ7FJIUVASG","created_at":"2026-07-05T03:58:24.674496+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSQ7FJIUVASGPFPZ","created_at":"2026-07-05T03:58:24.674496+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSQ7FJIU","created_at":"2026-07-05T03:58:24.674496+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/PSQ7FJIUVASGPFPZZVC2FFOSZ5","json":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5.json","graph_json":"https://pith.science/api/pith-number/PSQ7FJIUVASGPFPZZVC2FFOSZ5/graph.json","events_json":"https://pith.science/api/pith-number/PSQ7FJIUVASGPFPZZVC2FFOSZ5/events.json","paper":"https://pith.science/paper/PSQ7FJIU"},"agent_actions":{"view_html":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5","download_json":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5.json","view_paper":"https://pith.science/paper/PSQ7FJIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09664&json=true","fetch_graph":"https://pith.science/api/pith-number/PSQ7FJIUVASGPFPZZVC2FFOSZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/PSQ7FJIUVASGPFPZZVC2FFOSZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5/action/storage_attestation","attest_author":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5/action/author_attestation","sign_citation":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5/action/citation_signature","submit_replication":"https://pith.science/pith/PSQ7FJIUVASGPFPZZVC2FFOSZ5/action/replication_record"}},"created_at":"2026-07-05T03:58:24.674496+00:00","updated_at":"2026-07-05T03:58:24.674496+00:00"}