{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RM4IWJBZMJHB63UOR64YNA2X6O","short_pith_number":"pith:RM4IWJBZ","schema_version":"1.0","canonical_sha256":"8b388b2439624e1f6e8e8fb9868357f389e067022edf15a20e3851c3a5efa4bb","source":{"kind":"arxiv","id":"2106.04015","version":3},"attestation_state":"computed","paper":{"title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Angelos Filos, Balaji Lakshminarayanan, D. Sculley, Dustin Tran, Faris Sbahi, Florian Wenzel, Ghassen Jerfel, Jasper Snoek, Jeremiah Liu, Jeremy Nixon, Jie Ren, Josip Djolonga, Kevin Murphy, Mark Collier, Marton Havasi, Michael W. Dusenberry, Neil Band, Qixuan Feng, Rodolphe Jenatton, Sebastian Farquhar, Shreyas Padhy, Tim G. J. Rudner, Yarin Gal, Yeming Wen, Zachary Nado, Zelda Mariet","submitted_at":"2021-06-07T23:57:32Z","abstract_excerpt":"High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ability to compare techniques for improving these estimates is therefore very important for research and practice alike. Yet, competitive comparisons of methods are often lacking due to a range of reasons, including: compute availability for extensive tuning, incorporation of sufficiently many baselines, and concrete documentation for reproducibility. In this paper we introduce Uncertainty Baselines: high-quality imple"},"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":"2106.04015","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T23:57:32Z","cross_cats_sorted":[],"title_canon_sha256":"733f7e4b8cec320dc374622cd8e08e70bd87818e123308016c0b9e93753c1f30","abstract_canon_sha256":"f32d2c79f808e5eed9c1c6dbe01ef509e27020b2d0b8d6adaa1a1a7ba5298d5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:13.463619Z","signature_b64":"TC/NeFW8gUjCKm87Hj3/4WVtR34f5Dp6JRgDbFKPzmIZ1GYii9Ak5jzO1WPOqJwVJ+vf2cVtjcDDkUzw7vU1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b388b2439624e1f6e8e8fb9868357f389e067022edf15a20e3851c3a5efa4bb","last_reissued_at":"2026-07-05T03:46:13.463128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:13.463128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Angelos Filos, Balaji Lakshminarayanan, D. Sculley, Dustin Tran, Faris Sbahi, Florian Wenzel, Ghassen Jerfel, Jasper Snoek, Jeremiah Liu, Jeremy Nixon, Jie Ren, Josip Djolonga, Kevin Murphy, Mark Collier, Marton Havasi, Michael W. Dusenberry, Neil Band, Qixuan Feng, Rodolphe Jenatton, Sebastian Farquhar, Shreyas Padhy, Tim G. J. Rudner, Yarin Gal, Yeming Wen, Zachary Nado, Zelda Mariet","submitted_at":"2021-06-07T23:57:32Z","abstract_excerpt":"High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ability to compare techniques for improving these estimates is therefore very important for research and practice alike. Yet, competitive comparisons of methods are often lacking due to a range of reasons, including: compute availability for extensive tuning, incorporation of sufficiently many baselines, and concrete documentation for reproducibility. In this paper we introduce Uncertainty Baselines: high-quality imple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04015","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/2106.04015/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":"2106.04015","created_at":"2026-07-05T03:46:13.463185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04015v3","created_at":"2026-07-05T03:46:13.463185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04015","created_at":"2026-07-05T03:46:13.463185+00:00"},{"alias_kind":"pith_short_12","alias_value":"RM4IWJBZMJHB","created_at":"2026-07-05T03:46:13.463185+00:00"},{"alias_kind":"pith_short_16","alias_value":"RM4IWJBZMJHB63UO","created_at":"2026-07-05T03:46:13.463185+00:00"},{"alias_kind":"pith_short_8","alias_value":"RM4IWJBZ","created_at":"2026-07-05T03:46:13.463185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26990","citing_title":"Decision-Aligned Evaluation of Uncertainty Quantification","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30188","citing_title":"CalArena: A Large-Scale Post-Hoc Calibration Benchmark","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05592","citing_title":"When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O","json":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O.json","graph_json":"https://pith.science/api/pith-number/RM4IWJBZMJHB63UOR64YNA2X6O/graph.json","events_json":"https://pith.science/api/pith-number/RM4IWJBZMJHB63UOR64YNA2X6O/events.json","paper":"https://pith.science/paper/RM4IWJBZ"},"agent_actions":{"view_html":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O","download_json":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O.json","view_paper":"https://pith.science/paper/RM4IWJBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04015&json=true","fetch_graph":"https://pith.science/api/pith-number/RM4IWJBZMJHB63UOR64YNA2X6O/graph.json","fetch_events":"https://pith.science/api/pith-number/RM4IWJBZMJHB63UOR64YNA2X6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O/action/storage_attestation","attest_author":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O/action/author_attestation","sign_citation":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O/action/citation_signature","submit_replication":"https://pith.science/pith/RM4IWJBZMJHB63UOR64YNA2X6O/action/replication_record"}},"created_at":"2026-07-05T03:46:13.463185+00:00","updated_at":"2026-07-05T03:46:13.463185+00:00"}