{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JR3OG3MIADCLVPIRSMA7GCOSTY","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":"70742ccf09ea78f69f91f9c80a39be6b2a01075c5255559f2a7145fe49478f6a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T07:49:00Z","title_canon_sha256":"2d49a7cb4a6791ebbda3cbf276795c361f70185dee8eabfb5384ca22781c8731"},"schema_version":"1.0","source":{"id":"2608.10605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10605","created_at":"2026-08-12T01:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10605v1","created_at":"2026-08-12T01:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10605","created_at":"2026-08-12T01:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"JR3OG3MIADCL","created_at":"2026-08-12T01:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"JR3OG3MIADCLVPIR","created_at":"2026-08-12T01:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"JR3OG3MI","created_at":"2026-08-12T01:22:51Z"}],"graph_snapshots":[{"event_id":"sha256:075df9dd037a8ba359dde4a87ee085e367b513490702a6427931aa9e4592b6fd","target":"graph","created_at":"2026-08-12T01:22:51Z","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/2608.10605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage selects an architecture and training recipe, optimizing loss under compute constraints, and a separate systems stage then optimizes the implementation for hardware efficiency. In this work, we develop MOSAIC, which formulates model architecture and systems co-design as an optimization problem. MOSAIC couples a predictive scaling law with a calibrated performance model that estimates Model FLOPs Utilization (MFU), communication cost, memory footprint","authors_text":"Sheng Zha, Soumajyoti Sarkar, Yuxin Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T07:49:00Z","title":"Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10605","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:e28de6112416970530d8dbd7261e5f57d7792179f88e0d2abaae3516432dba0f","target":"record","created_at":"2026-08-12T01:22:51Z","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":"70742ccf09ea78f69f91f9c80a39be6b2a01075c5255559f2a7145fe49478f6a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T07:49:00Z","title_canon_sha256":"2d49a7cb4a6791ebbda3cbf276795c361f70185dee8eabfb5384ca22781c8731"},"schema_version":"1.0","source":{"id":"2608.10605","kind":"arxiv","version":1}},"canonical_sha256":"4c76e36d8800c4babd119301f309d29e0f5b249d878a647beeef3b376913437f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c76e36d8800c4babd119301f309d29e0f5b249d878a647beeef3b376913437f","first_computed_at":"2026-08-12T01:22:51.133464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:22:51.133464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UhXKG7GeHMnm/v5I9WB4CLjA5v3ZzaFmr1jSy0p7DajKgcJqj6Y71LgnzH0ZiwtdOphNAChUlqTUYH/FUAKNBw==","signature_status":"signed_v1","signed_at":"2026-08-12T01:22:51.135079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e28de6112416970530d8dbd7261e5f57d7792179f88e0d2abaae3516432dba0f","sha256:075df9dd037a8ba359dde4a87ee085e367b513490702a6427931aa9e4592b6fd"],"state_sha256":"7d03dd4f8eb64e1f0be98c894420717bf8414e23184095e018c24b1e2fa82566"}