{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ITL63L75FTQ2CFBVCDSWF6BGFW","short_pith_number":"pith:ITL63L75","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"},"canonical_sha256":"44d7edaffd2ce1a1143510e562f8262dad5bf19a0977093d4d86c7699fc054e2","source":{"kind":"arxiv","id":"2606.24020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24020","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24020v1","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24020","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"ITL63L75FTQ2","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"ITL63L75FTQ2CFBV","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"ITL63L75","created_at":"2026-06-24T01:14:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ITL63L75FTQ2CFBVCDSWF6BGFW","target":"record","payload":{"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"},"canonical_sha256":"44d7edaffd2ce1a1143510e562f8262dad5bf19a0977093d4d86c7699fc054e2","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"},"source_kind":"arxiv","source_id":"2606.24020","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":"2026-06-24T01:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bqiikXUCfXnrbffhrPX5Vgx2j26YhgkbMhcBlLGWiyjVjo3qFXDszZpIkRue0jJhQpwatq3bPxKwA8WQZS9NAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T04:23:50.555924Z"},"content_sha256":"6d690ea49562b26acd81eda58c6b235e3e540262842f6fe22ce38c65f93db934","schema_version":"1.0","event_id":"sha256:6d690ea49562b26acd81eda58c6b235e3e540262842f6fe22ce38c65f93db934"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ITL63L75FTQ2CFBVCDSWF6BGFW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23khg5e4z5pJINgOube8VxRV4m8PzpT9Dt4PQ/bZr/1R86dSbFkp6bgLxLhtymo9wPAJbqnEpgCiSNhBPovEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T04:23:50.556294Z"},"content_sha256":"d1ceb373a84a55e2781bb4a3345cef926dd95aa6daebedb866f8555abc25b6cc","schema_version":"1.0","event_id":"sha256:d1ceb373a84a55e2781bb4a3345cef926dd95aa6daebedb866f8555abc25b6cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/bundle.json","state_url":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/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":"2026-07-05T04:23:50Z","links":{"resolver":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW","bundle":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/bundle.json","state":"https://pith.science/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ITL63L75FTQ2CFBVCDSWF6BGFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ITL63L75FTQ2CFBVCDSWF6BGFW","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":"8a10e2c82a50e466a6f2b318203fbb6ebc238c78db369113cb7b6a319cd10b7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:54:00Z","title_canon_sha256":"4271f62970c5e0a85e28a3b4d8181ce2741bd253cd5c866951e9a352be1814be"},"schema_version":"1.0","source":{"id":"2606.24020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24020","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24020v1","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24020","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"ITL63L75FTQ2","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"ITL63L75FTQ2CFBV","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"ITL63L75","created_at":"2026-06-24T01:14:38Z"}],"graph_snapshots":[{"event_id":"sha256:d1ceb373a84a55e2781bb4a3345cef926dd95aa6daebedb866f8555abc25b6cc","target":"graph","created_at":"2026-06-24T01:14:38Z","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/2606.24020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Dimitris Papailiopoulos, Yuchen Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:54:00Z","title":"You Don't Need to Run Every Eval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24020","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":"sha256:6d690ea49562b26acd81eda58c6b235e3e540262842f6fe22ce38c65f93db934","target":"record","created_at":"2026-06-24T01:14:38Z","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":"8a10e2c82a50e466a6f2b318203fbb6ebc238c78db369113cb7b6a319cd10b7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:54:00Z","title_canon_sha256":"4271f62970c5e0a85e28a3b4d8181ce2741bd253cd5c866951e9a352be1814be"},"schema_version":"1.0","source":{"id":"2606.24020","kind":"arxiv","version":1}},"canonical_sha256":"44d7edaffd2ce1a1143510e562f8262dad5bf19a0977093d4d86c7699fc054e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44d7edaffd2ce1a1143510e562f8262dad5bf19a0977093d4d86c7699fc054e2","first_computed_at":"2026-06-24T01:14:38.319882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:38.319882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HaFiNrG6+jL/i0H0/CI4UXSSxN3yiXv6wAJE383+jOwBiQZ6KHWsQAWPdJ2QfCVD6ClnSZFKK+FTOz2B5fMVDg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:38.320366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d690ea49562b26acd81eda58c6b235e3e540262842f6fe22ce38c65f93db934","sha256:d1ceb373a84a55e2781bb4a3345cef926dd95aa6daebedb866f8555abc25b6cc"],"state_sha256":"969990e157886ed0eb40648ad26b64dfa670f83a94b55fa321789f48c3d7280c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YSXcfxifi7EgWTF/dajoxpTNfJbg3cZwEDadNGBcC3L6i/yoOPbAkkBe9UCpVSRrpjMCY36T/tMxpJXI4h1pAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T04:23:50.558311Z","bundle_sha256":"2208a5c0428da60dc364c9a9ee6c6b8165299b7119321510c5431b7c3ec92a86"}}