{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OOYBLIWOC7Z4BVHIRHWESVUJJ3","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":"cab566424273db9fc094f4ff013daa214ccd3184ce33999b13c4aa1127dbcd8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T10:20:47Z","title_canon_sha256":"3fced67521c802376d8b52472991cb04a0c79cf04ebd460565e5321cb31f47c5"},"schema_version":"1.0","source":{"id":"2606.26836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26836","created_at":"2026-06-26T01:16:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26836v1","created_at":"2026-06-26T01:16:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26836","created_at":"2026-06-26T01:16:01Z"},{"alias_kind":"pith_short_12","alias_value":"OOYBLIWOC7Z4","created_at":"2026-06-26T01:16:01Z"},{"alias_kind":"pith_short_16","alias_value":"OOYBLIWOC7Z4BVHI","created_at":"2026-06-26T01:16:01Z"},{"alias_kind":"pith_short_8","alias_value":"OOYBLIWO","created_at":"2026-06-26T01:16:01Z"}],"graph_snapshots":[{"event_id":"sha256:406523a716bab7cd1e860e76bfd1d12cf5b5def8ee58d0514efbb740877fed56","target":"graph","created_at":"2026-06-26T01:16:01Z","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/2606.26836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particularly under heterogeneous data distributions: (i) different models get different questions correct according to their specializations, and (ii) given a budget, multiple generations can be sampled and selectively retained. To quantify this gap, we introduce the Capability Frontier: a Pareto frontier over a set of models that characterizes the best achievable performance at each cost level under optimal selection across models and generations (i.e.","authors_text":"Amirali Abdullah, Ant\\'ia Garc\\'ia, Bradley Fowler, Daniel Thi Graviet, Fazl Barez, Joshua Greaves, Narmeen Fatimah Oozeer, Philip Quirke, Ryan Smith, Shriyash Kaustubh Upadhyay, William Myers","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T10:20:47Z","title":"The Capability Frontier: Benchmarks Miss 82% of Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26836","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:d478b343752b3364f292d23da19074cb2ad6a63374d79c732b60f8b5974d87ae","target":"record","created_at":"2026-06-26T01:16:01Z","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":"cab566424273db9fc094f4ff013daa214ccd3184ce33999b13c4aa1127dbcd8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T10:20:47Z","title_canon_sha256":"3fced67521c802376d8b52472991cb04a0c79cf04ebd460565e5321cb31f47c5"},"schema_version":"1.0","source":{"id":"2606.26836","kind":"arxiv","version":1}},"canonical_sha256":"73b015a2ce17f3c0d4e889ec4956894ed45c44c9fdd4ae3f407d9e1c94d26f3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73b015a2ce17f3c0d4e889ec4956894ed45c44c9fdd4ae3f407d9e1c94d26f3a","first_computed_at":"2026-06-26T01:16:01.249876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:01.249876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6YvC2q+qCrPjMV/N82I2hEFsMV54iotMIeWFVU+n94HThJj/G2O96LWijHNaFtIAvFpVtDPd5i5GJYRd6gDBg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:01.250284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d478b343752b3364f292d23da19074cb2ad6a63374d79c732b60f8b5974d87ae","sha256:406523a716bab7cd1e860e76bfd1d12cf5b5def8ee58d0514efbb740877fed56"],"state_sha256":"21b9c672f883f3f7507bafb110ac86c31570c08d98e42843021c5bf41fa6b913"}