{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M5BXKIC5CTHEB27LQIJWP3WGZQ","short_pith_number":"pith:M5BXKIC5","canonical_record":{"source":{"id":"2508.13144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T17:56:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8a9df34b06884f44d371b18e01c3a1bde49518d1bf8065ac9100555b000d775","abstract_canon_sha256":"8a7f557e91803a0d0ad0c2058acf98868d109f24d7031eb4db24c53a0f72e904"},"schema_version":"1.0"},"canonical_sha256":"674375205d14ce40ebeb821367eec6cc38d8b38c29bb4d4ffa111e3ab28c4f40","source":{"kind":"arxiv","id":"2508.13144","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13144","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13144v1","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13144","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"M5BXKIC5CTHE","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"pith_short_16","alias_value":"M5BXKIC5CTHEB27L","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"pith_short_8","alias_value":"M5BXKIC5","created_at":"2026-07-05T11:55:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M5BXKIC5CTHEB27LQIJWP3WGZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.13144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T17:56:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8a9df34b06884f44d371b18e01c3a1bde49518d1bf8065ac9100555b000d775","abstract_canon_sha256":"8a7f557e91803a0d0ad0c2058acf98868d109f24d7031eb4db24c53a0f72e904"},"schema_version":"1.0"},"canonical_sha256":"674375205d14ce40ebeb821367eec6cc38d8b38c29bb4d4ffa111e3ab28c4f40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:33.086445Z","signature_b64":"lbnYFuMw1QsYm9QQ80v9ttFPC3ALaCD34zpoSbu107hOXodHxxaaS3E8XYWEcOSm4WiaHr8OaCm9DGAx578MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"674375205d14ce40ebeb821367eec6cc38d8b38c29bb4d4ffa111e3ab28c4f40","last_reissued_at":"2026-07-05T11:55:33.085959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:33.085959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.13144","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":"2026-07-05T11:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBKYd/bkTCaQ+AAvsl2/xU7tqwazq5T/Q3AuT1ppajoKuIA9PKVb0fiWAC30EzBQY9QeRbhzuVyotOTOpG17Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:09:26.517004Z"},"content_sha256":"a52e96d2bd864b41d28235f5c9ef1daa82085340ce4d6c055516609f10a07b85","schema_version":"1.0","event_id":"sha256:a52e96d2bd864b41d28235f5c9ef1daa82085340ce4d6c055516609f10a07b85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M5BXKIC5CTHEB27LQIJWP3WGZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Heineman, Hannaneh Hajishirzi, Ian Magnusson, Jesse Dodge, Kyle Lo, Noah A. Smith, Valentin Hofmann, Yuling Gu","submitted_at":"2025-08-18T17:56:04Z","abstract_excerpt":"Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more reliable for such decisions, and interventions to design higher-quality evaluation benchmarks. We introduce two key metrics that show differences in current benchmarks: signal, a benchmark's ability to separate better models from worse models, and noise, a benchmark's sensitivity to random variability between training steps. We demonstrate that benchmarks with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13144","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/2508.13144/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":"2026-07-05T11:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eInWa+0bM2U2Ao9EIsMYAw6+kS1BmIMi5FmFuIdcfRxbEd7jx+0JmR/ZtalrhEpqyiT8Z4YTpFRZeUBV4WaPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:09:26.517620Z"},"content_sha256":"caf32c2ecb3fd8f799027b7a87684eae30621d9e92601e3bb8d98d830a7a0020","schema_version":"1.0","event_id":"sha256:caf32c2ecb3fd8f799027b7a87684eae30621d9e92601e3bb8d98d830a7a0020"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ/bundle.json","state_url":"https://pith.science/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ/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":"2026-08-10T09:09:26Z","links":{"resolver":"https://pith.science/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ","bundle":"https://pith.science/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ/bundle.json","state":"https://pith.science/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5BXKIC5CTHEB27LQIJWP3WGZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M5BXKIC5CTHEB27LQIJWP3WGZQ","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":"8a7f557e91803a0d0ad0c2058acf98868d109f24d7031eb4db24c53a0f72e904","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T17:56:04Z","title_canon_sha256":"d8a9df34b06884f44d371b18e01c3a1bde49518d1bf8065ac9100555b000d775"},"schema_version":"1.0","source":{"id":"2508.13144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13144","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13144v1","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13144","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"M5BXKIC5CTHE","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"pith_short_16","alias_value":"M5BXKIC5CTHEB27L","created_at":"2026-07-05T11:55:33Z"},{"alias_kind":"pith_short_8","alias_value":"M5BXKIC5","created_at":"2026-07-05T11:55:33Z"}],"graph_snapshots":[{"event_id":"sha256:caf32c2ecb3fd8f799027b7a87684eae30621d9e92601e3bb8d98d830a7a0020","target":"graph","created_at":"2026-07-05T11:55:33Z","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/2508.13144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more reliable for such decisions, and interventions to design higher-quality evaluation benchmarks. We introduce two key metrics that show differences in current benchmarks: signal, a benchmark's ability to separate better models from worse models, and noise, a benchmark's sensitivity to random variability between training steps. We demonstrate that benchmarks with ","authors_text":"David Heineman, Hannaneh Hajishirzi, Ian Magnusson, Jesse Dodge, Kyle Lo, Noah A. Smith, Valentin Hofmann, Yuling Gu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T17:56:04Z","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13144","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:a52e96d2bd864b41d28235f5c9ef1daa82085340ce4d6c055516609f10a07b85","target":"record","created_at":"2026-07-05T11:55:33Z","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":"8a7f557e91803a0d0ad0c2058acf98868d109f24d7031eb4db24c53a0f72e904","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T17:56:04Z","title_canon_sha256":"d8a9df34b06884f44d371b18e01c3a1bde49518d1bf8065ac9100555b000d775"},"schema_version":"1.0","source":{"id":"2508.13144","kind":"arxiv","version":1}},"canonical_sha256":"674375205d14ce40ebeb821367eec6cc38d8b38c29bb4d4ffa111e3ab28c4f40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"674375205d14ce40ebeb821367eec6cc38d8b38c29bb4d4ffa111e3ab28c4f40","first_computed_at":"2026-07-05T11:55:33.085959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:33.085959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lbnYFuMw1QsYm9QQ80v9ttFPC3ALaCD34zpoSbu107hOXodHxxaaS3E8XYWEcOSm4WiaHr8OaCm9DGAx578MBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:33.086445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a52e96d2bd864b41d28235f5c9ef1daa82085340ce4d6c055516609f10a07b85","sha256:caf32c2ecb3fd8f799027b7a87684eae30621d9e92601e3bb8d98d830a7a0020"],"state_sha256":"9682a88857d38bf4df98eb0d9a6a84ac3761f9c76eeaa0b9816ce7e2660102e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GLoN2LOJUd2tvZKymgD8xb2AUrtpjd9XZpd09b78YWqxJpru+Wfw03aHwcfe92ozhRHhcLmB59pIfTw2FwohAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:09:26.523056Z","bundle_sha256":"fc7e316d3f62aec17cd9cd330c6c9cb0d4b30653846343d482a499ba45075da8"}}