{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M544ZWX5C4FLULL5Z67ZUZPJWK","short_pith_number":"pith:M544ZWX5","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"},"canonical_sha256":"6779ccdafd170aba2d7dcfbf9a65e9b2b1a34ba4e50c3619228817d1f70a3857","source":{"kind":"arxiv","id":"2501.04234","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04234","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04234v1","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04234","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"M544ZWX5C4FL","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"pith_short_16","alias_value":"M544ZWX5C4FLULL5","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"pith_short_8","alias_value":"M544ZWX5","created_at":"2026-07-05T09:58:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M544ZWX5C4FLULL5Z67ZUZPJWK","target":"record","payload":{"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"},"canonical_sha256":"6779ccdafd170aba2d7dcfbf9a65e9b2b1a34ba4e50c3619228817d1f70a3857","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"},"source_kind":"arxiv","source_id":"2501.04234","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Qtp8tVkDIUQubDECJ7AseF9rPDndoCNXCkKqCXLB2Mx7Q1wOdtaTnKb2+yMzbwsWPuIt71bT653tAcWHVLkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:59:03.332642Z"},"content_sha256":"d2926c002764a67c5a567e1c43158fc476b40516ce6821f6bd6f47566663b808","schema_version":"1.0","event_id":"sha256:d2926c002764a67c5a567e1c43158fc476b40516ce6821f6bd6f47566663b808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M544ZWX5C4FLULL5Z67ZUZPJWK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tidGhMttBRrWFtngM9mbY7N7MNB4aToKz8D2Z3FeSdR5k20CkfIF/0uE7uHTMxS71wp+UDYHvNAFddb9e450DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:59:03.333228Z"},"content_sha256":"c87b4bffac997f1747ffba21b82ac343adee51b875058226521df198290c5f47","schema_version":"1.0","event_id":"sha256:c87b4bffac997f1747ffba21b82ac343adee51b875058226521df198290c5f47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/bundle.json","state_url":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T12:59:03Z","links":{"resolver":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK","bundle":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/bundle.json","state":"https://pith.science/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M544ZWX5C4FLULL5Z67ZUZPJWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M544ZWX5C4FLULL5Z67ZUZPJWK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4828d60379c360500dd1ef7d9fba06e8b3d0afb38da7c010ed9183f7ed429616","cross_cats_sorted":["cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-08T02:17:34Z","title_canon_sha256":"0811369444287973d323636d9fd672e38f0934b65459cf1ae9faf192152fc1aa"},"schema_version":"1.0","source":{"id":"2501.04234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04234","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04234v1","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04234","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"M544ZWX5C4FL","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"pith_short_16","alias_value":"M544ZWX5C4FLULL5","created_at":"2026-07-05T09:58:32Z"},{"alias_kind":"pith_short_8","alias_value":"M544ZWX5","created_at":"2026-07-05T09:58:32Z"}],"graph_snapshots":[{"event_id":"sha256:c87b4bffac997f1747ffba21b82ac343adee51b875058226521df198290c5f47","target":"graph","created_at":"2026-07-05T09:58:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.04234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Emily Casleton, Giri Gopalan, Rachel Longjohn","cross_cats":["cs.LG","stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-08T02:17:34Z","title":"Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04234","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2926c002764a67c5a567e1c43158fc476b40516ce6821f6bd6f47566663b808","target":"record","created_at":"2026-07-05T09:58:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4828d60379c360500dd1ef7d9fba06e8b3d0afb38da7c010ed9183f7ed429616","cross_cats_sorted":["cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-08T02:17:34Z","title_canon_sha256":"0811369444287973d323636d9fd672e38f0934b65459cf1ae9faf192152fc1aa"},"schema_version":"1.0","source":{"id":"2501.04234","kind":"arxiv","version":1}},"canonical_sha256":"6779ccdafd170aba2d7dcfbf9a65e9b2b1a34ba4e50c3619228817d1f70a3857","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6779ccdafd170aba2d7dcfbf9a65e9b2b1a34ba4e50c3619228817d1f70a3857","first_computed_at":"2026-07-05T09:58:32.062970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:32.062970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rAnrHzxl7cAf2A9gNxhXzzN19y7mFZQcJmPba8/oBGuJtKoATtrFy21lWioG0s2S7gzAa+ixmmf0nWTihrW8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:32.063330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2926c002764a67c5a567e1c43158fc476b40516ce6821f6bd6f47566663b808","sha256:c87b4bffac997f1747ffba21b82ac343adee51b875058226521df198290c5f47"],"state_sha256":"cf8033a935c942ef9efa74496b364b967d31eca1bb7355babc54dc688ade256b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SzHJxC9ZmdjMBJj148RDHiUQmI3xr0RKK3RJYG+jApIQfP3DweoAWiz6v7lw+vVOaVYHNkKKf+rY8nLgwxrlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:59:03.339134Z","bundle_sha256":"e1dda756a1915f463786c8e526c4f9460d280888015ff874e9096473fa7f1f41"}}