{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ITL63L75FTQ2CFBVCDSWF6BGFW","short_pith_number":"pith:ITL63L75","schema_version":"1.0","canonical_sha256":"44d7edaffd2ce1a1143510e562f8262dad5bf19a0977093d4d86c7699fc054e2","source":{"kind":"arxiv","id":"2606.24020","version":1},"attestation_state":"computed","paper":{"title":"You Don't Need to Run Every Eval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Yuchen Zeng","submitted_at":"2026-06-22T23:54:00Z","abstract_excerpt":"A modern model release reports scores on 40+ benchmarks and the same evaluations were run many more times before it: to track training progress, compare design choices, and select the checkpoint for the release. But do we need to run every eval? We compile a public score matrix of 84 frontier models on 133 benchmarks (2,604 cells, 23.3% filled) and find it is approximately rank-2: a model's scores across all 133 benchmarks are largely determined by just two numbers. We confirm this in two ways: scores hidden from the matrix are best recovered using two factors, and two factors already explain "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.24020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"4271f62970c5e0a85e28a3b4d8181ce2741bd253cd5c866951e9a352be1814be","abstract_canon_sha256":"8a10e2c82a50e466a6f2b318203fbb6ebc238c78db369113cb7b6a319cd10b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:38.320366Z","signature_b64":"HaFiNrG6+jL/i0H0/CI4UXSSxN3yiXv6wAJE383+jOwBiQZ6KHWsQAWPdJ2QfCVD6ClnSZFKK+FTOz2B5fMVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44d7edaffd2ce1a1143510e562f8262dad5bf19a0977093d4d86c7699fc054e2","last_reissued_at":"2026-06-24T01:14:38.319882Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:38.319882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Don't Need to Run Every Eval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Yuchen Zeng","submitted_at":"2026-06-22T23:54:00Z","abstract_excerpt":"A modern model release reports scores on 40+ benchmarks and the same evaluations were run many more times before it: to track training progress, compare design choices, and select the checkpoint for the release. But do we need to run every eval? We compile a public score matrix of 84 frontier models on 133 benchmarks (2,604 cells, 23.3% filled) and find it is approximately rank-2: a model's scores across all 133 benchmarks are largely determined by just two numbers. We confirm this in two ways: scores hidden from the matrix are best recovered using two factors, and two factors already explain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24020","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/2606.24020/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.24020","created_at":"2026-06-24T01:14:38.319935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24020v1","created_at":"2026-06-24T01:14:38.319935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24020","created_at":"2026-06-24T01:14:38.319935+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITL63L75FTQ2","created_at":"2026-06-24T01:14:38.319935+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITL63L75FTQ2CFBV","created_at":"2026-06-24T01:14:38.319935+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITL63L75","created_at":"2026-06-24T01:14:38.319935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW","json":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW.json","graph_json":"https://pith.science/api/pith-number/ITL63L75FTQ2CFBVCDSWF6BGFW/graph.json","events_json":"https://pith.science/api/pith-number/ITL63L75FTQ2CFBVCDSWF6BGFW/events.json","paper":"https://pith.science/paper/ITL63L75"},"agent_actions":{"view_html":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW","download_json":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW.json","view_paper":"https://pith.science/paper/ITL63L75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24020&json=true","fetch_graph":"https://pith.science/api/pith-number/ITL63L75FTQ2CFBVCDSWF6BGFW/graph.json","fetch_events":"https://pith.science/api/pith-number/ITL63L75FTQ2CFBVCDSWF6BGFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/action/storage_attestation","attest_author":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/action/author_attestation","sign_citation":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/action/citation_signature","submit_replication":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/action/replication_record"}},"created_at":"2026-06-24T01:14:38.319935+00:00","updated_at":"2026-06-24T01:14:38.319935+00:00"}