{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AUKWHIXQAIQ3YATBMWJLZP5QAU","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":"b401ccf4ad4c8edfa0316314a59100fe2f2e1c39bf1f414689d3d14b0d4c493f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T19:51:55Z","title_canon_sha256":"6ea2580c60b3fa239ea8e1cb4aa1c6e255ebeba807f0d9e3c17d1b291978aca3"},"schema_version":"1.0","source":{"id":"2607.28801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28801","created_at":"2026-08-03T00:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28801v1","created_at":"2026-08-03T00:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28801","created_at":"2026-08-03T00:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"AUKWHIXQAIQ3","created_at":"2026-08-03T00:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"AUKWHIXQAIQ3YATB","created_at":"2026-08-03T00:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"AUKWHIXQ","created_at":"2026-08-03T00:12:57Z"}],"graph_snapshots":[{"event_id":"sha256:a0b0b0abf38f804c5bcdd716d22201910407aa7801521fd49c006354a181ffcb","target":"graph","created_at":"2026-08-03T00:12:57Z","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/2607.28801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples. We introduce a dataset-centric meta-evaluation framework that audits benchmark datasets at the sample level along five latent dimensions: 1. Cognitive and Knowledge Demands, 2. Language and Content Quality, 3. Task Properties, 4. Context, and 5. Ethics, Safety, and Fairness. Applying this framework, we annotate five influential benchmarks -- MMLU, ARC, WinoGrande, HellaSwag, and TruthfulQA -- revea","authors_text":"Jordan Sassoon, Philipp D. Siedler","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T19:51:55Z","title":"Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28801","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:eaa1271212507f219b9f93ff0f93bb3c299a19368d651f26fe04bb1f03f92a43","target":"record","created_at":"2026-08-03T00:12:57Z","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":"b401ccf4ad4c8edfa0316314a59100fe2f2e1c39bf1f414689d3d14b0d4c493f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T19:51:55Z","title_canon_sha256":"6ea2580c60b3fa239ea8e1cb4aa1c6e255ebeba807f0d9e3c17d1b291978aca3"},"schema_version":"1.0","source":{"id":"2607.28801","kind":"arxiv","version":1}},"canonical_sha256":"051563a2f00221bc02616592bcbfb0052c2e184b5a40810a2ba517e14a7549f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"051563a2f00221bc02616592bcbfb0052c2e184b5a40810a2ba517e14a7549f5","first_computed_at":"2026-08-03T00:12:57.554591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T00:12:57.554591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MpHrEQRwzo5+LJ9UYP9tZBPfuy9OzuDEQS06pCaQBq7rX+snKTTo1hVvab1hsJ8/rqKjTVvb1C0KeUx8SbgdBg==","signature_status":"signed_v1","signed_at":"2026-08-03T00:12:57.556921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaa1271212507f219b9f93ff0f93bb3c299a19368d651f26fe04bb1f03f92a43","sha256:a0b0b0abf38f804c5bcdd716d22201910407aa7801521fd49c006354a181ffcb"],"state_sha256":"27ab0fccc4aebda120481ae3e2dcfa22e20f2f6146c9bdeb14aa6ee53e5484c5"}