{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LJ7RWJ2MFDSZB6D3DIY36SSAGQ","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":"46b2ceba45918f9ac4afd19d6883f6e48cff52467466b715511237ce130ef93c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T18:42:01Z","title_canon_sha256":"785d109acf1d3053fa787413cc65c12fa2056f47481b7c0438fa1af9cebdbea5"},"schema_version":"1.0","source":{"id":"2306.00008","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00008","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00008v2","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00008","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"LJ7RWJ2MFDSZ","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"LJ7RWJ2MFDSZB6D3","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"LJ7RWJ2M","created_at":"2026-07-05T08:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:bd4a295988fbc588c7df3a23d3b58c00bd834cdc6ca1b79b1e35d9af0410a5dc","target":"graph","created_at":"2026-07-05T08:11:53Z","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/2306.00008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers are central to recent successes in natural language processing and computer vision. Transformers have a mostly uniform backbone where layers alternate between feed-forward and self-attention in order to build a deep network. Here we investigate this design choice and find that more complex blocks that have different permutations of layer primitives can be more efficient. Using this insight, we develop a complex block, named Brainformer, that consists of a diverse sets of layers such as sparsely gated feed-forward layers, dense feed-forward layers, attention layers, and various for","authors_text":"Andrew Dai, Chang Lan, Claire Cui, Da Huang, Daiyi Peng, David So, James Laudon, Jeff Dean, Nan Du, Quoc Le, Siamak Shakeri, Yanping Huang, Yanqi Zhou, Yifeng Lu, Zhifeng Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T18:42:01Z","title":"Brainformers: Trading Simplicity for Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00008","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":"sha256:4ecdb77c7e8910a3b9dde04a30756ecd09d659b199ac1139e27cfdff99aa954c","target":"record","created_at":"2026-07-05T08:11:53Z","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":"46b2ceba45918f9ac4afd19d6883f6e48cff52467466b715511237ce130ef93c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T18:42:01Z","title_canon_sha256":"785d109acf1d3053fa787413cc65c12fa2056f47481b7c0438fa1af9cebdbea5"},"schema_version":"1.0","source":{"id":"2306.00008","kind":"arxiv","version":2}},"canonical_sha256":"5a7f1b274c28e590f87b1a31bf4a4034184fd1f63057914630567b4196e307bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a7f1b274c28e590f87b1a31bf4a4034184fd1f63057914630567b4196e307bf","first_computed_at":"2026-07-05T08:11:53.079515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:53.079515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I91Ta1O+pPsM3BZVTsg61oZVukatwwEqTfvKzpHXkUdSbvPPNZIR9l/MSxkos2yYU/3ff2nDVLJbfV98j/wSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:53.079932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00008","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ecdb77c7e8910a3b9dde04a30756ecd09d659b199ac1139e27cfdff99aa954c","sha256:bd4a295988fbc588c7df3a23d3b58c00bd834cdc6ca1b79b1e35d9af0410a5dc"],"state_sha256":"cc33adcb68a4c9e37d93bac94ab6fca4f60e5539030a507d1baba84d2c7e4cdc"}