{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2XLH6DKMQDHJKJN7YLDBKEDFLH","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":"78cc358d4dbecf93fee907d2cfb4844377eb76669b2c06a59cda3c097fab79ef","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T17:46:56Z","title_canon_sha256":"a35c89bee64e0a5b65f073928db1cedcff3460ef1d73be9127623a2f4a50cb2c"},"schema_version":"1.0","source":{"id":"2406.04391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04391","created_at":"2026-07-05T10:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04391v2","created_at":"2026-07-05T10:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04391","created_at":"2026-07-05T10:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"2XLH6DKMQDHJ","created_at":"2026-07-05T10:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"2XLH6DKMQDHJKJN7","created_at":"2026-07-05T10:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"2XLH6DKM","created_at":"2026-07-05T10:10:23Z"}],"graph_snapshots":[{"event_id":"sha256:333886661692c8ac3c9072576f3852b8d3e47b8fadf9498e6a517a365a981d42","target":"graph","created_at":"2026-07-05T10:10:23Z","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/2406.04391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predicting changes from scaling advanced AI systems is a desirable property for engineers, economists, governments and industry alike, and, while a well-established literature exists on how pretraining performance scales, predictable scaling behavior on downstream capabilities remains elusive. While many factors are certainly responsible, this paper identifies a significant factor that makes predicting scaling behavior on widely used multiple-choice question answering benchmarks challenging and illuminates a path towards making such downstream evaluations predictable with scale. Using five mod","authors_text":"Adam Ibrahim, Brando Miranda, Gabriel Mukobi, Hailey Schoelkopf, Herbie Bradley, Rylan Schaeffer, Sanmi Koyejo, Stella Biderman, Varun Madan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T17:46:56Z","title":"Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04391","kind":"arxiv","version":2},"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":"sha256:15f898969253b7b7bf1401787260e02ff7753ef28e6e32e90ed5d4eae040db8f","target":"record","created_at":"2026-07-05T10:10:23Z","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":"78cc358d4dbecf93fee907d2cfb4844377eb76669b2c06a59cda3c097fab79ef","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T17:46:56Z","title_canon_sha256":"a35c89bee64e0a5b65f073928db1cedcff3460ef1d73be9127623a2f4a50cb2c"},"schema_version":"1.0","source":{"id":"2406.04391","kind":"arxiv","version":2}},"canonical_sha256":"d5d67f0d4c80ce9525bfc2c615106559cbe364b4688f8588d72e7407339a5fdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5d67f0d4c80ce9525bfc2c615106559cbe364b4688f8588d72e7407339a5fdb","first_computed_at":"2026-07-05T10:10:23.806146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:23.806146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XCIicZCVDUD4WsApqZ83a3TkjBRtJEpYko+jt00csObj6d6ZoAAtr3dArS6CoS5DwqSK7gBuROftWaB75nm8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:23.806637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15f898969253b7b7bf1401787260e02ff7753ef28e6e32e90ed5d4eae040db8f","sha256:333886661692c8ac3c9072576f3852b8d3e47b8fadf9498e6a517a365a981d42"],"state_sha256":"e187dbc2cb81af937b156c8ccbf9f02ad3fccc319853d556496c2122bd63d613"}