{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M544ZWX5C4FLULL5Z67ZUZPJWK","short_pith_number":"pith:M544ZWX5","schema_version":"1.0","canonical_sha256":"6779ccdafd170aba2d7dcfbf9a65e9b2b1a34ba4e50c3619228817d1f70a3857","source":{"kind":"arxiv","id":"2501.04234","version":1},"attestation_state":"computed","paper":{"title":"Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.AP"],"primary_cat":"stat.ML","authors_text":"Emily Casleton, Giri Gopalan, Rachel Longjohn","submitted_at":"2025-01-08T02:17:34Z","abstract_excerpt":"Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus and then adapted to solve a variety of downstream tasks. To summarize performance across multiple tasks, evaluation metrics are often aggregated into a summary metric, e.g., average accuracy across 10 question-answering tasks. When aggregating evaluation metrics, it is useful to incorporate uncertainty in the aggregate metric in order to gain a more realistic understanding of model performance. Our objective in this work is to demonstrate how statistical"},"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":"2501.04234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-08T02:17:34Z","cross_cats_sorted":["cs.LG","stat.AP"],"title_canon_sha256":"0811369444287973d323636d9fd672e38f0934b65459cf1ae9faf192152fc1aa","abstract_canon_sha256":"4828d60379c360500dd1ef7d9fba06e8b3d0afb38da7c010ed9183f7ed429616"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:32.063330Z","signature_b64":"rAnrHzxl7cAf2A9gNxhXzzN19y7mFZQcJmPba8/oBGuJtKoATtrFy21lWioG0s2S7gzAa+ixmmf0nWTihrW8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6779ccdafd170aba2d7dcfbf9a65e9b2b1a34ba4e50c3619228817d1f70a3857","last_reissued_at":"2026-07-05T09:58:32.062970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:32.062970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.AP"],"primary_cat":"stat.ML","authors_text":"Emily Casleton, Giri Gopalan, Rachel Longjohn","submitted_at":"2025-01-08T02:17:34Z","abstract_excerpt":"Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus and then adapted to solve a variety of downstream tasks. To summarize performance across multiple tasks, evaluation metrics are often aggregated into a summary metric, e.g., average accuracy across 10 question-answering tasks. When aggregating evaluation metrics, it is useful to incorporate uncertainty in the aggregate metric in order to gain a more realistic understanding of model performance. Our objective in this work is to demonstrate how statistical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04234","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/2501.04234/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":"2501.04234","created_at":"2026-07-05T09:58:32.063024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04234v1","created_at":"2026-07-05T09:58:32.063024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04234","created_at":"2026-07-05T09:58:32.063024+00:00"},{"alias_kind":"pith_short_12","alias_value":"M544ZWX5C4FL","created_at":"2026-07-05T09:58:32.063024+00:00"},{"alias_kind":"pith_short_16","alias_value":"M544ZWX5C4FLULL5","created_at":"2026-07-05T09:58:32.063024+00:00"},{"alias_kind":"pith_short_8","alias_value":"M544ZWX5","created_at":"2026-07-05T09:58:32.063024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08679","citing_title":"Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23114","citing_title":"A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23102","citing_title":"Unstable Rankings in Bayesian Deep Learning Evaluation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK","json":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK.json","graph_json":"https://pith.science/api/pith-number/M544ZWX5C4FLULL5Z67ZUZPJWK/graph.json","events_json":"https://pith.science/api/pith-number/M544ZWX5C4FLULL5Z67ZUZPJWK/events.json","paper":"https://pith.science/paper/M544ZWX5"},"agent_actions":{"view_html":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK","download_json":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK.json","view_paper":"https://pith.science/paper/M544ZWX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04234&json=true","fetch_graph":"https://pith.science/api/pith-number/M544ZWX5C4FLULL5Z67ZUZPJWK/graph.json","fetch_events":"https://pith.science/api/pith-number/M544ZWX5C4FLULL5Z67ZUZPJWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/action/storage_attestation","attest_author":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/action/author_attestation","sign_citation":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/action/citation_signature","submit_replication":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/action/replication_record"}},"created_at":"2026-07-05T09:58:32.063024+00:00","updated_at":"2026-07-05T09:58:32.063024+00:00"}