{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AP2TBU3KQLX4IMIIBMUBMH37MZ","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":"adbdb6e42994dec504bc54e0eab254dfb84c043a36fae76fb950269283e9acac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T08:56:58Z","title_canon_sha256":"3b53d443e2b19729e28685b4a460f54104bcc333137a943f25399aa5a41faa77"},"schema_version":"1.0","source":{"id":"2606.05169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05169","created_at":"2026-06-05T00:13:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05169v1","created_at":"2026-06-05T00:13:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05169","created_at":"2026-06-05T00:13:47Z"},{"alias_kind":"pith_short_12","alias_value":"AP2TBU3KQLX4","created_at":"2026-06-05T00:13:47Z"},{"alias_kind":"pith_short_16","alias_value":"AP2TBU3KQLX4IMII","created_at":"2026-06-05T00:13:47Z"},{"alias_kind":"pith_short_8","alias_value":"AP2TBU3K","created_at":"2026-06-05T00:13:47Z"}],"graph_snapshots":[{"event_id":"sha256:fd72dd88010658db23fc60c45fbef7079a296e6decf9ec2a29e8539eedf830d4","target":"graph","created_at":"2026-06-05T00:13:47Z","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/2606.05169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We give a stereological theory of LLM benchmark coverage. For any suite with effective dimensionality d_eff, the visible Hausdorff distance between two convex capability profiles consistent with the same scores is bounded by epsilon + C R m^(-1/(d_eff-1)), with matching Lipschitz lower bound. Empirically, three independent leaderboards (Open LLM v2, an extended 12-benchmark suite, LiveBench) all have d_eff in [2.86, 4.80] on their competitive frontier; the structural blind spot exceeds the observed runner-up score gap by two orders of magnitude and dominates statistical noise by 52-127x. Under","authors_text":"Jason Z Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T08:56:58Z","title":"The Evaluation Blind Spot: A Stereological Theory of Benchmark Coverage for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05169","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":"sha256:6c81a5f479e9ecb78cc1ab83f07d5bc7be51f0c2afca7ae382bddbb2e39f521c","target":"record","created_at":"2026-06-05T00:13:47Z","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":"adbdb6e42994dec504bc54e0eab254dfb84c043a36fae76fb950269283e9acac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T08:56:58Z","title_canon_sha256":"3b53d443e2b19729e28685b4a460f54104bcc333137a943f25399aa5a41faa77"},"schema_version":"1.0","source":{"id":"2606.05169","kind":"arxiv","version":1}},"canonical_sha256":"03f530d36a82efc431080b28161f7f6655fcea77ad1e2d32189bbd644d22f809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03f530d36a82efc431080b28161f7f6655fcea77ad1e2d32189bbd644d22f809","first_computed_at":"2026-06-05T00:13:47.549250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:47.549250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kLkQZwtlrAVk+C/KzZZ3cIOPSOgkSLNFRAL1cnSVXSo/D0rE9x40ldPfJUJLioZXxKQnHMQ3UvmCjIjV2fc/Aw==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:47.549857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c81a5f479e9ecb78cc1ab83f07d5bc7be51f0c2afca7ae382bddbb2e39f521c","sha256:fd72dd88010658db23fc60c45fbef7079a296e6decf9ec2a29e8539eedf830d4"],"state_sha256":"60b5de395f7f79fc1994fe5dc66dba296dddf18e984e465e320b86c2fb8d3e02"}